The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
A Duality Based Approach for Realtime TV-L 1 Optical Flow
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A reasonable explanation is that the temporal network is actually designed to capture different visual aspects of videos compared to the spatial network, which indicates that the feature distributions are more diverse between those fields (e.g., optical flow and RGB) [20], [24], [25].”
From Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval (2019) · cites this paper as [24]
Citations
Cites
Nonlinear total variation based noise removal algorithms
Rudin, L., Osher, S., & Fatemi, E. (1992) · Physica D Nonlinear Phenomena · doi:10.1016/0167-2789(92)90242-f · Cited by 17,214
Horn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312
Horn, B. K. P., & Schunck, B. G. (1981) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.965761 · Cited by 7,443
chambolle (2004) · doi:10.1023/b:jmiv.0000011321.19549.88 · Cited by 3,227
High Accuracy Optical Flow Estimation Based on a Theory for Warping
Brox, T., Bruhn, A., Papenberg, N., & Weickert, J. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_3 · Cited by 2,634
A computational framework and an algorithm for the measurement of visual motion
Anandan, P. (1989) · International Journal of Computer Vision · doi:10.1007/bf00158167 · Cited by 1,073
Thormaehlen, T., Broszio, H., & Weißenfeld, A. (2004) · Lecture notes in computer science · doi:10.1007/b97865 · Cited by 901
Fast Global Minimization of the Active Contour/Snake Model
Bresson, X., Esedoḡlu, S., Vandergheynst, P., Thiran, J., & Osher, S. (2007) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-007-0002-0 · Cited by 857
A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration
Chan, T. F.-C., Golub, G. H., & Mulet, P. (1999) · SIAM Journal on Scientific Computing · doi:10.1137/s1064827596299767 · Cited by 849
An Algorithm for Total Variation Minimization and Applications
Chambolle, A. (2004) · Journal of Mathematical Imaging and Vision · doi:10.1023/b:jmiv.0000011325.36760.1e · Cited by 835
Cited by
Sorted by citations
Items 801–900 of 1,002
Han, Y., Zhang, P., Zhuo, T., Huang, W., & Zhang, Y. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.162 · Cited by 9
“Here, the optical flow fields between two adjacent frames were extracted by adopting the TVL1 optical flow algorithm [32].”
MethodReal-Time Simultaneous 3D Reconstruction and Optical Flow Estimation
Roxas, M., & Oishi, T. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00102 · Cited by 9
“For example, in [25] and [27], the optical flow is estimated by also using the TV-L1 minimization problem which is highly desirable because of its real-time implementation as well as accurate results.”
MethodLearned Collaborative Stereo Refinement
Knöbelreiter, P., & Pock, T. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01485-5 · Cited by 9
“The data-term measures usually the raw intensity difference [3,32,4] between the reference view and the warped other view.”
BackgroundMethodInfluentialSelf-citationMotion-Compensated Spatio-Temporal Filtering for Multi-Image and Multimodal Super-Resolution
Buades, A., Duran, J., & Navarro, J. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01200-5 · Cited by 9
“Since they are not available in a real scenario, the variational superresolution methods described previously first compute the displacement fields using optical flow techniques (Brox et al. 2004; Zach et al. 2007; Weinzaepfel et al. 2013).”
MethodInfluentialPredicting Appearance of Vehicles From Blind Spots Based on Pedestrian Behaviors at Crossroads
Hara, K., Kataoka, H., Inaba, M., Narioka, K., Hotta, R., & Satoh, Y. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3108795 · Cited by 9
Rollenbeck, R., Orellana‐Alvear, J., Rodríguez, R., Macalupu, S., & Nolasco, P. (2021) · Atmosphere · doi:10.3390/atmos12121561 · Cited by 9
Micro-Expression Recognition Based on Pixel Residual Sum and Cropped Gaussian Pyramid
Zhao, Y. C., Chen, Z., & Luo, S. (2021) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.746985 · Cited by 10
“flow (Zach et al., 2007) of the onset frame and the midposition frame, and then performs ME recognition through the Dual-Inception network.”
MethodApplications of Image-Based Computer Vision for Remote Surveillance of Slope Instability
Muhammad, M., Williams‐Jones, G., Stead, D., Tortini, R., Falorni, G., & Donati, D. (2022) · Frontiers in Earth Science · doi:10.3389/feart.2022.909078 · Cited by 9
“After applying a Taylor series expansion to the left hand side of the equation, it can be rewritten as follows (O’Donovan, 2005; Zach et al., 2007; Wedel et al., 2009; Hermle et al., 2022):”
MethodParallel Generalized Thresholding Scheme for Live Dense Geometry from a Handheld Camera
Stühmer, J., Gumhold, S., & Cremers, D. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_35 · Cited by 9
“In particular, the central algorithmic component, namely the thresholding scheme proposed in [1] for computing the primal variables can be generalized to the geometry reconstruction problem.”
BackgroundMethodInfluentialVideo composition by optimized 3D mean‐value coordinates
Shen, Y., Lin, X., Gao, Y., Sheng, B., & Liu, Q. (2012) · Computer Animation and Virtual Worlds · doi:10.1002/cav.1465 · Cited by 9
“Because all important parts of an algorithm such as optical flow algorithm [15], alpha matting algorithm [16], and MVC can all be run on a graphics processing unit, our algorithm can achieve high efficiency.”
MethodClustering Motion for Real-Time Optical Flow Based Tracking
Senst, T., Evangelio, R. H., Keller, I., & Sikora, T. (2012) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2012.20 · Cited by 9
“Very fast implementations of the KLT tracker [8] use parallelization [11], [5].”
MethodFast TV-L1 optical flow for interactivity
d'Angelo, E., Paratte, J., Puy, G., & Vandergheynst, P. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115836 · Cited by 9
“Figure 1 shows a comparison between the proposed scheme and an exact TV-L1 algorithm (we took [7] as reference).”
BackgroundMethodResultInfluentialComputer vision on the GPU — Tools, algorithms and frameworks
Fassold, H. (2016) · IEEE International Conference on Intelligent Engineering Systems (INES) · doi:10.1109/ines.2016.7555129 · Cited by 9
“In [5] an OpenCL implemention of the TV-L1 optical flow algorithm [22] is presented.”
MethodMulti-image super-resolution using a locally adaptive denoising-based refinement
Bätz, M., Koloda, J., Eichenseer, A., & Kaup, A. (2016) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2016.7813343 · Cited by 9
“For realworld video sequences with both global and local motion, this registration step can be done by either a block-based motion estimation technique [13] or by an optical flow method [14], [15].”
MethodComparisons of Visual Activity Primitives for Voice Activity Detection
Shahid, M., Beyan, C., & Murino, V. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30642-7_5 · Cited by 9
AWSD: Adaptive Weighted Spatiotemporal Distillation for Video Representation
Tavakolian, M., Tavakoli, H. R., & Hadid, A. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00811 · Cited by 9
“For the computation of the optical flow, we used TLV1 optical flow algo-rithm [40], which is implemented in OpenCV with CUDA.”
MethodDual-Branch Network With a Subtle Motion Detector for Microaction Recognition in Videos
Mi, Y., Zhang, X., Li, Z., & Wang, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2989864 · Cited by 9
“For each subsegment, the spatial-stream and temporal-stream networks take the input of a single RGB frame and optical flow stacks, respectively, where the optical flow is computed via the TVL1 optical flow algorithm [55].”
MethodPredicting Vehicles Appearing from Blind Spots Based on Pedestrian Behaviors
Hara, K., Kataoka, H., Inaba, M., Narioka, K., Hotta, R., & Satoh, Y. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294443 · Cited by 9
“We used the TV-L1 algorithm [28] implemented in OpenCV to calculate the optical flow.”
MethodLoL-V2T: Large-Scale Esports Video Description Dataset
Tanaka, T., & Simo‐Serra, E. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00513 · Cited by 10
“We also use tvl1 [35] for calculating optical flow.”
MethodFoveated convolutional neural networks for video summarization
Wu, J., Zhong, S.-H., Ma, Z., Heinen, S. J., & Jiang, J. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5953-1 · Cited by 9
“We select the widely used toolbox to obtain optical flow [38, 45].”
Real-Time End-to-End Action Detection with Two-Stream NetworksPreprint
El-Nouby, A., & Taylor, G. W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08362 · Cited by 9
“Previous two-stream approaches for solving action detection use non-trainable optical flow algorithms [5, 6, 7] that are completely separate from their detection model.”
MethodDeep Temporal Linear Encoding NetworksPreprint
Diba, A., Sharma, V., & Gool, L. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.06678 · Cited by 18
“For the extraction of the optical flow frames, we use the TVL1 optical flow algorithm [42] from the OpenCV toolbox with CUDA implementation.”
MethodZhou, L., Mao, Q., Huang, X., Zhang, F., & Zhang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.04838 · Cited by 9
“For FR, TV-L1 optical flow method [54] is utilized to obtain motion feature from the onset and apex frames of each micro-expression video.”
MethodDenoising-based Image Compression for ConnectomicsPreprint
Minnen, D. C., Januszewski, M., Blakely, T. M., Shapson-Coe, A., Schalek, R. L., Ballé, J., Lichtman, J. W., & Jain, V. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.05.29.445828 · Cited by 9
3D network with channel excitation and knowledge distillation for action recognition
Hu, Z., Mao, J., Yao, J., & Bi, S. (2023) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2023.1050167 · Cited by 8
“In this paper, the TV-L1 (Zach et al., 2007) method is used to extract the optical flow, and the default parameter settings of OpenCV are used.”
MethodVideo-Based Analysis of Cattle Behaviors: Improved Classification Using FlowEQ Transform
Chae, J.-W., Sim, H., Lee, C., Choi, C.-S., & Cho, H. (2024) · IEEE Access · doi:10.1109/access.2024.3379277 · Cited by 9
“Consequently, optical flow methods that are based on deep learning or require high processing costs were excluded, and the Dual TV-L1 optical flow was used [29].”
MethodHFA-Net: hierarchical feature aggregation network for micro-expression recognition
Zhang, M., Yang, W., Wang, L., Wu, Z., & Chen, D. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01804-0 · Cited by 9
“Thus, We employed the widely used TV-L1 [37] algorithm as the optical flow estimation method.”
3-D Mediated Detection and Tracking in Wide Area Aerial Surveillance
Chen, B.-J., & Medioni, G. G. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.59 · Cited by 8
“The dense optical flow [27] takes about 1.”
BackgroundMethodInfluentialEfficient frame-sequential label propagation for video object segmentation
Chen, Y., Hao, C., Wu, W., & Wu, E. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4520-5 · Cited by 8
“Furthermore, it can recover a better motion shape than TV-L1 algorithm thanks to our mask supervisor, which is so important for segmenting the similar color around object boundary.”
BackgroundMethodInfluentialThe GAN That Warped: Semantic Attribute Editing With Unpaired Data
Dorta, G., Vicente, S., Campbell, N. D. F., & Simpson, I. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00540 · Cited by 8
Temporal Micro-Action Localization for Videofluoroscopic Swallowing Study
Ruan, X., Dai, M., Chen, Z., You, Z., Zhang, Y., Li, Y., Dou, Z., & Tan, M. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3313255 · Cited by 8
“The detailed process is as follows: First, the TV-L1 method [38] is used to extract optical flow frames, and the RGB data and optical flow data are separately input into the I3D model to obtain the dual-stream features of the input video.”
MethodA New Benchmark In Vivo Paired Dataset for Laparoscopic Image De-smoking
Xia, W., Fan, V., Peters, T. M., & Chen, E. C. S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72378-0_1 · Cited by 8
On a Decomposition Model for Optical Flow
Abhau, J., Belhachmi, Z., & Scherzer, O. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03641-5_10 · Cited by 8
Integrating approximate depth data into dense image correspondence estimation
Ruhl, K., Klose, F., Lipski, C., & Magnor, M. A. (2012) · doi:10.1145/2414688.2414692 · Cited by 8
“12 in [34]):”
BackgroundMethodInfluentialTemporal Attentive Network for Action Recognition
Shi, Y., Tian, Y., Huang, T., & Wang, Y. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486452 · Cited by 8
“To extract optical flow, we choose the TVL1 optical flow algorithm [30] and use the OpenCV GPU implementation.”
MethodHierarchical Motion Estimation for Small Objects in Frame-Rate Up-Conversion
Thang, N. V., Choi, J., Hong, J.-H., Kim, J.-S., & Lee, H. (2018) · IEEE Access · doi:10.1109/access.2018.2875688 · Cited by 8
“[21] compute the smoothness term with an L1 norm of motion vector difference between neighboring ones.”
MethodSchön, C., Dittrich, J., & Müller, R. W. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330682 · Cited by 8
“han directly deriving features from satellite images, our approach is based on the error resulting from forecasting the next image based on previous images using optical flow algorithms such as TV-L1 [27]. A high-level overview of our approach is shown in Figure 1. The core idea can be formulated as follows: The movem…”
MethodRecognizing Micro Actions in Videos: Learning Motion Details via Segment-Level Temporal Pyramid
Mi, Y., & Wang, S. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00182 · Cited by 8
“For each sub-segment, the spatial stream and temporal stream networks take the input of a single RGB frame and optical flow stacks respectively, where optical flow is computed via TVL1 optical flow algorithm [18] implemented in OpenCV [19].”
MethodNavarro, J., & Buades, A. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.07.005 · Cited by 8
Roheda, S., & Krim, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6870 · Cited by 12
“The Optical Flow is computed using the TV-L1 algorithm (Zach et al., 2007).”
MethodSingle-Stage End-to-End Temporal Activity Detection in Untrimmed Videos
Rahman, M. A., & Laganière, R. (2020) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv50864.2020.00035 · Cited by 7
“Optical flow is computed using TV-L1 algorithm [40].”
MethodA robust optical flow motion estimation and correction method for IRT imaging in brain surgery
Moshaei-Nezhad, Y., Müller, J., Schnabel, C., Kirsch, M., & Tetzlaff, R. (2020) · Quantitative InfraRed Thermography Journal · doi:10.1080/17686733.2020.1766892 · Cited by 8
SHCFNet on Micro-expression Recognition System
Jie, H. J., Zhao, X., & Zheng, L. (2020) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei51763.2020.9263671 · Cited by 8
Tong, M., Yan, K., Jin, L., Yue, X., & Li, M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05698-0 · Cited by 8
“The TVL1 optical flow algorithm [49] that implemented in OpenCV is chosen for the extraction of optical flows.”
MethodWang, B., Zhao, Y., & Zhang, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.086 · Cited by 8
Human Embryo Cell Centroid Localization and Counting in Time-Lapse Sequences
Lockhart, L., Saeedi, P., Au, J., & Havelock, J. C. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412801 · Cited by 8
“Optical flow diagrams [27] that contextualize cell movement between frames were added as another secondary input to indicate temporal relationship to the previous frame predicted mask.”
BackgroundMethodSingle trunk multi-scale network for micro-expression recognition
Wang, J., Pan, X., Li, X., Wei, G., & Zhou, Y. (2021) · Graphics and Visual Computing · doi:10.1016/j.gvc.2021.200026 · Cited by 8
Micro-Expression Recognition Base on Optical Flow Features and Improved MobileNetV2
Xu, W. H., Zheng, H., Yang, Z., & Yang, Y. (2021) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2021.06.002 · Cited by 8
“In order to be able to improve the robustness of the method as much as possible, the optical flow technique adopted for the method in this paper is TV-L1 [33] method described above.”
MethodMatch Cutting: Finding Cuts with Smooth Visual Transitions
Chen, B., Ziai, A., Tucker, R. S., & Xie, Y. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00215 · Cited by 13
“Optical flow has been traditionally formulated as an optimization problem [32, 16, 78] or as a gradient-based estimation.”
MethodLiu, X., & Alim, U. (2015) · Computer Graphics Forum · doi:10.1111/cgf.12622 · Cited by 8
Progressive 3D Model Acquisition with a Commodity Hand-Held Camera
Kang, Z., & Medioni, G. G. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.43 · Cited by 8
“Dense optical flow: we compute the dense optical flow between the previous frame In−1 and the current frame In using Total-Variation L1 (TV-L1) optical flow [22], which minimizes an L1 norm data term and a totalvariation regularization term:”
MethodOn improving the robustness of variational optical flow against illumination changes
Mohamed, M. A., Rashwan, H. A., Mertsching, B., García, M. Á., & Puig, D. (2013) · doi:10.1145/2510650.2510660 · Cited by 8
Ignakov, D., Okouneva, G., & Liu, G. (2012) · Autonomous Robots · doi:10.1007/s10514-012-9297-9 · Cited by 8
“The optical flow algorithm used for 3D reconstruction is based on the approach outlined in Zach et al. (2007).”
MethodApproximate inference for spatial functional data on massively parallel processors
Rakêt, L. L., & Markussen, B. (2013) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2013.10.016 · Cited by 8
“The chromatograms have been registered in retention time using a so-called TV-L1 warping algorithm (Zach et al. 2007, Rakêt et al. 2011).”
MethodTemporally consistent video matting based on bilayer segmentation
Tang, Z., Miao, Z., & Wan, Y. (2010) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2010.5583894 · Cited by 8
“(vx,vy) is the moving vector at (x0, y0), and is calculated by the backward optical flow [15].”
Real-time motion supression in TOF range images
Hussmann, S. H., Hermanski, A., & Edeler, T. (2010) · Conference proceedings - IEEE Instrumentation/Measurement Technology Conference · doi:10.1109/imtc.2010.5488283 · Cited by 8
“By using a GPU based implementation [10] it was possible to produce satisfying results at a frame rate of about 10 fps.”
MethodLocal part model for action recognition
Shi, F., Laganière, R., & Petriu, E. M. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2015.11.010 · Cited by 8
Action recognition using log-covariance matrices of silhouette and optical-flow features
Ishwar, P., Konrad, J., & Guo, K. (2012) · Cited by 8
Can We Jointly Register and Reconstruct Creased Surfaces by Shape-from-Template Accurately?
Gallardo, M., Collins, T., & Bartoli, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46493-0_7 · Cited by 8
“Other problems such as optical flow [31, 32] use M-estimators for handling non-smooth solutions, and this gave much inspiration.”
BackgroundSpatio-Temporal Video Completion in Spherical Image Sequences
Xu, B., Pathak, S., Fujii, H., Yamashita, A., & Asama, H. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2718106 · Cited by 8
“Here the total variation (TV) model [17] is adopted to capture this prior information: where ∇ denotes the gradient operator.”
BackgroundMethodSpontaneous Versus Posed Smiles—Can We Tell the Difference?
Mandal, B., & Ouarti, N. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-2107-7_24 · Cited by 8
Integrating Gaussian mixture model and dilated residual network for action recognition in videos
Fang, M., Bai, X., Zhao, J., Yang, F., Hung, C.-C., & Liu, S. (2020) · Multimedia Systems · doi:10.1007/s00530-020-00683-4 · Cited by 8
Online Spatio-Temporal Action Detection in Long-Distance Imaging Affected by the Atmosphere
Chen, E., Haik, O., & Yitzhak Yitzhaky, B. (2021) · IEEE Access · doi:10.1109/access.2021.3057172 · Cited by 8
“For the optical flow stream, we implemented several methods: the TV-L1 [46], which is based on the classic gradient approach, and deep-learning based methods, namely, LiteFlowNet [30], and PWC-Net [29].”
MethodAccuracy improvement in human detection using HOG features on train-mounted camera
Saika, S., Takahashi, S., Takeuchi, M., & Katto, J. (2016) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2016.7800373 · Cited by 8
“We tried Gunner Farneback method [4] and Dual TVL1 method [5] which are representative methods in OpenCV [6] for optical flow estimation.”
MethodHigh Performance Parallel Optical Flow Algorithms on the Sony Playstation 3.
Gwosdek, P., Bruhn, A., & Weickert, J. (2008) · Vision Modeling and Visualization · Cited by 8
The EPIC-KITCHENS Dataset: Collection, Challenges and BaselinesPreprint
Damen, D., Doughty, H., Farinella, G. M., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.00343 · Cited by 8
“Evaluation Metrics: We report two sets of metrics: aggregate and per-class, which are equivalent to the class-agnostic and classaware metrics in [12].”
BackgroundResultSelf-supervised training for blind multi-frame video denoising
Dewil, V., Anger, J., Davy, A., Ehret, T., Facciolo, G., & Arias, P. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00277 · Cited by 7
“Following [18], the warping transformations are estimated using the TV-L1 optical flow method [62, 50], as it gives consistent results across noise types and intensities.”
MethodWang, Y., Zhang, Q., & Shu, X. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03221-1 · Cited by 7
“In this paper, we use the TV-L1 [44] to extract optical flow information which is obtained from the onset and apex frames of each micro-expression video.”
Parikh, C., Saluja, R., Jawahar, C. V., & Sarvadevabhatla, R. K. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10609989 · Cited by 7
“The optical flow frames are extracted using the TVL1 algorithm [22] implemented in OpenCV.”
MethodMeasurement of large, discontinuous displacement from digital images
Luo, Z., Hu, X., Wang, L., & Lu, Y. (2020) · Strain · doi:10.1111/str.12349 · Cited by 7
“[41] The previous quantification of errors is performed on the synthetic images obtained by applying subpixel displacements on the reference image.”
MethodRecent Advances in Video Action Recognition with 3D Convolutions
Hara, K. (2020) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2020imp0012 · Cited by 9
“Inspired by the TV-L1 algorithm [43], which is an optical flow estimation method, Piergiovanni et al.”
MethodRusso, P., Ticca, S., Alati, E., & Pirri, F. (2021) · IEEE Access · doi:10.1109/access.2021.3050514 · Cited by 7
“The first preprocessing stream is the optical flow, computed according to the dualTV-L1 method of [30].”
MethodMontagnon, T., Giffard‐Roisin, S., Mura, M. D., Marchandon, M., Pathier, E., & Hollingsworth, J. (2024) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000174 · Cited by 7
Khan, M., Mahala, N. K., & Kumar, P. (2023) · Sadhana · doi:10.1007/s12046-023-02318-6 · Cited by 7
“The work presented in [27–29] employed total variational regularization (TV) and L 1 -norm in the estimation.”
Bi, S., Hu, Z., Zhang, H., Di, J., & Sun, Z. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110713 · Cited by 7
AI-Powered Anomaly and Threat Detection for Surveillance Footage Analysis
Sivapriya, J., Ramani, D. R., Srivastava, R. P., Kumar, K., & Nair, R. V. (2024) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc62624.2024.00048 · Cited by 7
Gehrig, S. K., & Franke, U. (2015) · Springer eBooks · doi:10.1007/978-3-319-09840-1_22-1 · Cited by 7
Colour harmonisation for images and videos via two-level graph cut
Tang, Z., Miao, Z., Wan, Y., & Jesse, F. F. (2011) · IET Image Processing · doi:10.1049/iet-ipr.2010.0335 · Cited by 7
Intelligent Traffic Information System a Real-Time Traffic Information System on the Shiraz Bypass
Sodagaran, A., Zarei, N., & Azimifar, Z. (2016) · MATEC Web of Conferences · doi:10.1051/matecconf/20168104003 · Cited by 7
Lee, J. T., & Park, E. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00919-9_38 · Cited by 7
Learned Collaborative Stereo Refinement
Knöbelreiter, P., & Pock, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33676-9_1 · Cited by 7
Self-citationA New Real-Time Embedded Video Denoising Algorithm
Petreto, A., Romera, T., Lemaitre, F., Masliah, I., Gaillard, B., Bouyer, M., Meunier, Q. L., & Lacassagne, L. (2019) · Conference on Design and Architectures for Signal and Image Processing · doi:10.1109/dasip48288.2019.9049189 · Cited by 7
“Therefore, we decided to use the TV-L1 algorithm to compute the optical flow, since it satisfies all these constraints [24].”
MethodSelf-supervised video representation learning by maximizing mutual information
Xue, F., Ji, H., Zhang, W., & Cao, Y. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115967 · Cited by 7
Learning to Adapt to Unseen Abnormal Activities Under Weak Supervision
Park, J., Kim, J., & Han, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69541-5_31 · Cited by 7
An unsupervised approach for traffic motion patterns extraction
Moradi, A., Shahbahrami, A., & Akoushideh, A. (2020) · IET Image Processing · doi:10.1049/ipr2.12033 · Cited by 7
“To compare the performance of optical flow algorithms, we use two different optical flow algorithms to extract motion vectors, Lucas–Kanade [10] as a sparse optical flow and dual TV-L1 [11] as a dense optical flow.”
MethodWen, J., Yang, W., Wang, L.-J., Wei, W., Tan, S., & Yong-zhi, W. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-0010-4_12 · Cited by 8
Latent label mining for group activity recognition in basketball videos
Wu, L., Li, Z., Xiang, Y., Jian, M., & Shen, J. (2021) · IET Image Processing · doi:10.1049/ipr2.12265 · Cited by 7
Effective action recognition with embedded key point shifts
Cao, H., Xu, Y., Yang, J., Mao, K., Yin, J., & See, S. C. W. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108172 · Cited by 7
Robust optical flow estimation to enhance behavioral research on ants
Rao, S., Wang, H., Kashif, R., & Rao, F. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103284 · Cited by 7
Rethinking Lightweight: Multiple Angle Strategy for Efficient Video Action Recognition
Chen, J., Wang, Z., Zeng, K., He, Z., & Xiong, Z. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3144074 · Cited by 7
Implementations Impact on Iterative Image Processing for Embedded GPU
Romera, T., Petreto, A., Lemaitre, F., Bouyer, M., Meunier, Q., & Lacassagne, L. (2021) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco54536.2021.9615947 · Cited by 7
“First introduced by Zach, Pock and Bischof in 2007, the TV-L1 optical flow is an iterative numerical scheme based on the minimisation of an energy function [10].”
BackgroundMethodInfluentialSelf-supervised Video Representation Learning with Cascade Positive Retrieval
Wu, C.-E. R., Lai, F., Hu, Y. H., & Kadav, A. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00452 · Cited by 7
“To generate optical flow maps from the video, we use TV-L1 [43] to extract the flow view with a third channel filled with zeros.”
MethodDewil, V., Barral, A., Facciolo, G., & Arias, P. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00537 · Cited by 7
“The MF2F results strongly depends on the optical flow accuracy, which is computed using the TV-L1method [36,49].”
MethodSuperWarp: Supervised Learning and Warping on U-Net for Invariant Subvoxel-Precise Registration
Young, S. I., Balbastre, Y., Dalca, A. V., Wells, W. M., Iglesias, J. E., & Fischl, B. R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-11203-4_12 · Cited by 7
Optical Flow Computation for Video Under the Dynamic Illumination
Chen, J., Duan, H., Song, Y., Cai, Z., & Yang, G. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3207583 · Cited by 7
“In recent years, although variational optical flow methods [6], [7], [8], [9], [10], [29], [32] that consist of a data term and a regularization term show outstanding performance for highly accurate optical flow estimation, their optical flow fields are often computed under ideal conditions, such as…”
BackgroundMethodDisplacement extraction of background-oriented schlieren images using Swin Transformer
Cai, H., Song, Y., Ji, Y., Li, Z., & He, A. (2023) · Journal of the Optical Society of America A · doi:10.1364/josaa.487192 · Cited by 7
A Closer Look at Video Sampling for Sequential Action Recognition
Zhang, Y., Zhao, J., Chen, Z., Mi, S., Zhu, H., & Geng, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3274108 · Cited by 7
“The optical flows are extracted by the TV-L1 algorithm [53] from the adjacent frames in the videos, the flow magnitude is truncated at [− 20 , 20 ] .”
MethodGoedrich, A., Koenig, D., Eilertsen, G., & Teutsch, M. (2023) · doi:10.1117/12.2663745 · Cited by 7
Leng, C., Ding, Q., Wu, C., Chen, A., Wang, H., & Wu, H. (2023) · The Visual Computer · doi:10.1007/s00371-023-03073-9 · Cited by 8
“∈ R T × W × H × 2 opposite the action sequence using the same T V − L 1 [48].”
Joint Denoising and HDR for RAW Image Sequences
Buades, A., Martorell, O., & Sánchez-Beeckman, M. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3354649 · Cited by 7
“Once we have applied the YUVW transformation, we compute the optical flow between the middle-exposed frame ˆ J ref and every other ˆ J i ∈ ˆ J on the brightness channel Y using the total variation approach in [79].”
Method
Metadata
- Authors
- Zach, C., Pock, T., & Bischof, H.
- Affiliations
- VRVis GmbH (Austria) (AT)
- Graz University of Technology (AT)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2007-09-21
- Pages
- 214-223
- OpenAlex
- W1578985305
- Cited by
- 1,658
- References
- 27
- Citations by year
- 2026: 44 · 2025: 62 · 2024: 83 · 2023: 111 · 2022: 107 · 2021: 188 · 2020: 152 · 2019: 149 · 2018: 112 · 2017: 98 · 2016: 88 · 2015: 99 · 2014: 70 · 2013: 59 · 2012: 56
- FWCI
- 27.93
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Springer eBooks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- optical flow, total variation regularization, GPU acceleration, real-time video processing, variational methods, discontinuity preservation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
