A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place
Open accessThe DOI matches its Crossref record; 32 of the 33 references it cites were found in a registry or an index.
Abstract
An important logistics application of robotics involves manipulators that pick-and-place objects placed in warehouse shelves. A critical aspect of this task corresponds to detecting the pose of a known object in the shelf using visual data. Solving this problem can be assisted by the use of an RGBD sensor, which also provides depth information beyond visual data. Nevertheless, it remains a challenging problem since multiple issues need to be addressed, such as low illumination inside shelves, clutter, texture-less and reflective objects as well as the limitations of depth sensors. This letter provides a new rich dataset for advancing the state-of-the-art in RGBD-based 3D object pose estimation, which is focused on the challenges that arise when solving warehouse pick-and-place tasks. The publicly available dataset includes thousands of images and corresponding ground truth data for the objects used during the first Amazon Picking Challenge at different poses and clutter conditions. Each image is accompanied with ground truth information to assist in the evaluation of algorithms for object detection. To show the utility of the dataset, a recent algorithm for RGBD-based pose estimation is evaluated in this letter. Given the measured performance of the algorithm on the dataset, this letter shows how it is possible to devise modifications and improvements to increase the accuracy of pose estimation algorithms. This process can be easily applied to a variety of different methodologies for object pose detection and improve performance in the domain of warehouse pick-and-place.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“Some standard RGB benchmarks for the task include CIFAR-10/100 [6], ImageNet [7], and PASCAL VOC [8].”
MethodThe Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 1×
“Some standard RGB benchmarks for the task include CIFAR-10/100 [6], ImageNet [7], and PASCAL VOC [8].”
MethodIndoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760 · cited 2×
“NYU Depth Dataset v2 [10]: The NYU dataset also focuses on indoor scenes, but ground truth labels are presented as full image segmentation.”
BackgroundResultA large-scale hierarchical multi-view RGB-D object dataset
Lai, K., Bo, L., Ren, X., & Fox, D. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5980382 · Cited by 1,316 · cited 7×
“Table-Top Object Dataset [12]: A collaboration between Willow Garage and the Univ. of Michigan, this dataset consists of ∼ 1,000 2.5D images with ground truth labels for 480 frames.”
ResultInfluentialHinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., & Navab, N. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37331-2_42 · Cited by 1,161 · cited 8×
“Table-Top Object Dataset [12]: A collaboration between Willow Garage and the Univ. of Michigan, this dataset consists of ∼ 1,000 2.5D images with ground truth labels for 480 frames.”
BackgroundMethodInfluentialModel globally, match locally: Efficient and robust 3D object recognition
Drost, B., Ulrich, M., Navab, N., & Ilic, S. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540108 · Cited by 981 · cited 1×
“of different algorithms for this problem, given the rich literature on the subject [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29].”
BackgroundGradient Response Maps for Real-Time Detection of Textureless Objects
Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., & Lepetit, V. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.206 · Cited by 610
CAD-model recognition and 6DOF pose estimation using 3D cues
Aldoma, A., Vincze, M., Blodow, N., Gossow, D., Gedikli, S., Rusu, R. B., & Bradski, G. (2011) · 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) · doi:10.1109/iccvw.2011.6130296 · Cited by 294 · cited 1×
“of different algorithms for this problem, given the rich literature on the subject [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29].”
BackgroundObject recognition and full pose registration from a single image for robotic manipulation
Collet, A., Berenson, D., Srinivasa, S. S., & Ferguson, D. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152739 · Cited by 275 · cited 1×
“of different algorithms for this problem, given the rich literature on the subject [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29].”
BackgroundA Category-Level 3D Object Dataset: Putting the Kinect to Work
Janoch, A., Karayev, S., Jia, Y., Barron, J. T., Fritz, M., Saenko, K., & Darrell, T. (2013) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-1-4471-4640-7_8 · Cited by 254 · cited 3×
“Segmented Scenes Datasets B3DO [9]: A project by UC Berkeley, the dataset contains >3,000 2.”
MethodResult
Research works printed but not linked: 4
- choi, 0, Proc IEEE/RSJ Int Conf Intell Robots Syst (IROS), 3342
- lai, 0, Proc AAAI Conf Artif Intell, 1474
- muja, 0, Proc IEEE Int Conf Robot Autom (ICRA), 2939
- steder, 0, Proc (IEEE/RSJ IROS) Workshop Defin Solv Realistic Percept Prob Pers Robot
Cited by
Items 101–182 of 182
Automation in library management using LabVIEW
Gade, A., & Angal, Y. S. (2016) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea.2016.7860133 · Cited by 9
“At last activity arranging and other counterfeit consciousness methods is utilized to work out the proper behaviour [7].”
MethodInferring 3D Shapes of Unknown Rigid Objects in Clutter Through Inverse Physics Reasoning
Song, C., & Boularias, A. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2885579 · Cited by 13
“In warehouses and factories, manipulated objects are typically known in advance, with their CAD models obtained from full 3D scans [5]–[8].”
Kiyokawa, T., Tomochika, K., Takamatsu, J., & Ogasawara, T. (2019) · Advanced Robotics · doi:10.1080/01691864.2019.1697750 · Cited by 9
Shape Completion Enabled Robotic GraspingPreprint
Varley, J., DeChant, C., Richardson, A., Ruales, J., & Allen, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.08546 · Cited by 25
“A alternative to general shape completion in the robotics community is object recognition and 3D pose detection [4][5][6].”
BackgroundCurved loop strip soft gripper
Liu, W., Qu, H., Wang, H., Wang, X., Kuang, Y., Hu, B., Li, X., Liu, D., Kuo, C., & Guo, S. (2025) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2025.110746 · Cited by 8
A 6DoF Pose Estimation Dataset and Network for Multiple Parametric Shapes in Stacked Scenarios
Zhang, X., Lv, W., & Zeng, L. (2021) · Machines · doi:10.3390/machines9120321 · Cited by 9
“The Rutgers APC dataset [22] contains 24 textured objects from the Amazon Picking Challenge 2015 [23] with 10,000 RGB-D images, which is designed for household cluttered scenarios.”
BackgroundMethodVirtual tactile POMDP-based path planning for object localization and grasping
Wang, C., Zang, X., Song, C., Liu, Z., Zhao, J., & Ang, M. H. (2024) · Measurement · doi:10.1016/j.measurement.2024.114480 · Cited by 8
Fu, X., Jiang, M., Hu, Z., Jin, Y., Meng, L., Du, R., & Liu, Q. (2024) · Marine and Petroleum Geology · doi:10.1016/j.marpetgeo.2024.106999 · Cited by 7
A Summary of the 4th International Workshop on Recovering 6D Object Pose
Hodaň, T., Kouskouridas, R., Kim, T., Tombari, F., Bekris, K. E., Drost, B., Groueix, T., Walas, K., Lepetit, V., Leonardis, A., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_36 · Cited by 11
Self-citationRapid Pose Label Generation through Sparse Representation of Unknown Objects
Singh, R., Benallegue, M., Yoshiyasu, Y., & Kanehiro, F. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561277 · Cited by 8
“Singh and Fumio Kanehiro are with University of Tsukuba, Ibaraki, Japan Techniques for (semi-) automating the process of training data generation has gained research interest in recent years [6], [7], [8], [9], [10].”
BackgroundMethod6D Object Localization in Car-Assembly Industrial Environment
Papadaki, A. I., & Pateraki, M. (2023) · Journal of Imaging · doi:10.3390/jimaging9030072 · Cited by 12
“LM [27], LM-O [28], HB [29], RU-APC [30], IC-MI [31] and YCB-V [32] contain objects of everyday life, depicted in complex scenes.”
BackgroundRT-less: a multi-scene RGB dataset for 6D pose estimation of reflective texture-less objects
Zhao, X., Li, Q., Chao, Y., Wang, Q., He, Z., & Liang, D. (2023) · The Visual Computer · doi:10.1007/s00371-023-03097-1 · Cited by 9
“Ru-APC [10] : This dataset contains 25 APC [11] objects.”
Automated Assembly Using 3D and 2D Cameras
Kleppe, A. L., Bjørkedal, A., Larsen, K. S., & Egeland, O. (2017) · Robotics · doi:10.3390/robotics6030014 · Cited by 6
“This makes them ideal for pick and place algorithms such as [10], but not for accurate assembly tasks.”
BackgroundObject recognition and pose estimation for modular manipulation system: Overview and initial results
Yun, W., Lee, J., Lee, J.-H., & Kim, J. (2017) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2017.7992711 · Cited by 7
“In a recent experiment, MOPED in the second approach and LINE-MOD in the third approach underperform in APC scenario [9][10].”
MethodDu, G., Wang, K., Lian, S., & Zhao, K. (2019) · arXiv (Cornell University) · Cited by 7
Evaluation of single-stage vision models for pose estimation of surgical instruments
Burton, W. S., Myers, C. A., Rutherford, M. J., & Rullkoetter, P. J. (2023) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-023-02890-6 · Cited by 8
PPN-Pack: Placement Proposal Network for Efficient Robotic Bin Packing
Pan, J.-H., Gao, X., Hui, K.-H., Zhu, S., Liu, Y., Heng, P., & Fu, C. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3385612 · Cited by 9
“Datasets: Following the setting of [11], we perform experiments on a set of 96 real-world objects: 71 from the YCB dataset [30] and 25 from Rutgers APC RGB-D dataset [31].”
MethodComparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation
Burde, V., Benbihi, A., Burget, P., & Sattler, T. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00745 · Cited by 12
“Pose evaluation datasets provide object CAD models, images depicting those objects in various positions and the object poses [10, 21,23,37,41,47,78,96,99,107].”
RobotP: A Benchmark Dataset for 6D Object Pose Estimation
Yuan, H., Hoogenkamp, T. R., & Veltkamp, R. C. (2021) · Sensors · doi:10.3390/s21041299 · Cited by 6
“Linemod [14] 2012 Yes No Household Yes RGB-D images, 3D models, object masks and bounding boxes KIT [26] 2012 Yes No Household No 2D images and 3D models Linemod-Occluded [27] 2014 Yes No Household Yes RGB-D images, 3D models, object masks and bounding boxes IC-MI [28] 2014 Yes No Household Yes RGB images and 3D model…”
BackgroundMethodIntelligent monitoring method of tridimensional storage system based on deep learning
Liu, M., Xu, X. G., Wang, X., Jiang, Q., & Liu, C. (2022) · Environmental Science and Pollution Research · doi:10.1007/s11356-022-20658-4 · Cited by 7
“The way of data acquisition by fixing the camera on a fixed robot or mobile forklift in the literature (Rennie et al. 2016) and (Tianjian et al. 2019) increases the hardware investment cost, interferes with the logistics vehicle of the goods, and the data collection will take a lot of time, which in turn makes the who…”
BackgroundMultimodal Design for Interactive Collaborative Problem-Solving Support
VanderHoeven, H., Bradford, M., Jung, C., Khebour, I., Lai, K., Pustejovsky, J. D., Krishnaswamy, N., & Blanchard, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60107-1_6 · Cited by 10
“To capture a sufficient amount of the scene in which a CPS task typically unfolds, the camera must be placed further away from the relevant objects that it typically has been in other 6DOF pose estimation tasks and datasets [44, 55].”
BackgroundLuh, Y.-P., Huang, L.-C., Lu, H.-J., & Chu, C. (2020) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-020-00211-9 · Cited by 6
Pattar, S. P., Killus, T., Hirakawa, T., Yamashita, T., Sawanobori, T., & Fujiyoshi, H. (2022) · Advanced Robotics · doi:10.1080/01691864.2022.2136504 · Cited by 6
“[18] Motoman SDA10F 100,000 6D Human annotation (Manual) Data collection: 5–10 s.”
MethodQ-PSO: Fast Quaternion-Based Pose Estimation from RGB-D Images
Rosa, S., Toscana, G., & Bona, B. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0714-3 · Cited by 8
“Recent tests of LINEMOD showed only 32% accuracy rates in an APC-like scenario [19].”
MethodATPS: an adaptive trajectory prediction system based on semantic information for dynamic objects
Zhang, J., Mi, Z., Guo, Y., Obaidat, M. S., & Fellow of, I. E. E. E. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05819-9 · Cited by 4
Recent advances on application of deep learning for recovering object pose
Li, W., Luo, Y., Wang, P., Qin, Z., Zhou, H., & Qiao, H. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866501 · Cited by 5
Lin, J.-A., Chiu, C., & Cheng, Y.-Y. (2021) · Journal of Signal Processing Systems · doi:10.1007/s11265-021-01677-9 · Cited by 5
Mobile Robotic Manipulator Based Autonomous Warehouse Operations
Øvsthus, Ø., Robsrud, D. N., Muggerud, L., Amendola, J., Cenkeramaddi, L. R., Tyapin, I., & Jha, A. (2023) · International Conference on Control, Mechatronics and Automation (ICCMA) · doi:10.1109/iccma59762.2023.10374743 · Cited by 7
The Detection of Non-Cooperative Targets in Space by Using 3D Point Cloud
Ding, Q., & He, J. (2019) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar.2019.8813367 · Cited by 5
“The nozzle is detected and the attitude is determined by the transformation relationship between the ellipse and the circle [6-10].”
BackgroundThe ACRV Picking Benchmark (APB): A Robotic Shelf Picking Benchmark to Foster Reproducible ResearchPreprint
Leitner, J., Tow, A. W., Dean, J. E., Suenderhauf, N., Durham, J. W., Cooper, M., Eich, M., Lehnert, C., Mangels, R., McCool, C., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.05258 · Cited by 5
“for object segmentation [15] and 6D pose estimation [16] can be contributed to the ubiquity of low-cost depth sensors.”
BackgroundTripicchio, P., D’Avella, S., & Avizzano, C. A. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1222465 · Cited by 6
“The Rutgers dataset (Rennie et al., 2015) consists of about 10K RGB-D images of hand-annotated 6DOF poses concerning 24 mostly textured objects involved in the cluttered warehouse environment of the Amazon Picking Challenge (APC) held in 2015 (Correll et al., 2018).”
BackgroundAutomatic graspability map generation based on shape-primitives for unknown and familiar objects
Eizicovits, D., & Berman, S. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.09.001 · Cited by 4
Ueno, K., Irie, G., Nishiyama, M., & Iwai, Y. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803383 · Cited by 4
“To evaluate the accuracy of object recognition and the error of pose estimation, we used three-dimensional mesh models of 17 objects included in the Rutgers APC RGB-D dataset [15].”
MethodDoraPicker: An Autonomous Picking System for General ObjectsPreprint
Zhang, H., Long, P., Zhou, D., Qian, Z., Wang, Z., Wan, W., Manocha, D., Park, C., Hu, T., Cao, C., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.06317 · Cited by 4
“As described in [12], LINEMOD is an object detection and pose estimation method, which takes a 3D mesh object model generated in advance as the input.”
BackgroundMethodAutomated AI-Based Annotation Framework for 3D Object Detection from LIDAR Data in Industrial Areas
Abdelhalim, G., Simon, K., Bensch, R., Parimi, S., & Qureshi, B. A. (2024) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2024-01-2999 · Cited by 3
Phuc, D. T., Nguyen, T. C., & Hieu, D. S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126923 · Cited by 5
dVPose: Automated Data Collection and Dataset for 6D Pose Estimation of Robotic Surgical Instruments
Greene, N., Luo, W., & Kazanzides, P. (2023) · International Symposium on Medical Robotics · doi:10.1109/ismr57123.2023.10130238 · Cited by 3
FocalPose++: Focal Length and Object Pose Estimation via Render and Compare
Cífka, M., Ponimatkin, G., Labbé, Y., Russell, B. C., Aubry, M., Petrík, V., & Šivic, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3475638 · Cited by 8
“The standard 6D pose estimation benchmarks [20], [31], [62], [63], [64] focus on the scenario with a known focal length.”
BackgroundDigitization Methods for a Logistics Warehouse Towards Digital Twin-Driven Optimization
Kawaguchi, N., Asai, Y., Kano, K., Takaki, K., Mori, Y., Suzuki, Y., Watanabe, K., Gushi, Y., Katayama, S., Urano, K., et al. (2025) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp65954.2025.00035 · Cited by 3
“Furthermore, [2] has released datasets for image recognition aimed at improving Pick & Place efficiency, such as those used in the Amazon Picking Challenge [3].”
CLUBS: An RGB-D dataset with cluttered box scenes containing household objects
Novković, T., Furrer, F., Panjek, M., Grinvald, M., Siegwart, R., & Nieto, J. I. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919875221 · Cited by 3
“Similarly, Rennie et al. (2016) have generated a dataset containing 25 object meshes that were used in the ARC.”
MethodOptimal Design of a Conveyor-Based Automatic Sorting System
Huang, M., Wu, J., Tang, Y., & Shi, L. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264520 · Cited by 3
“The second aspect is improving the identification accuracy [4].”
BackgroundTight Robot Packing in the Real World: A Complete Manipulation Pipeline with Robust PrimitivesPreprint
Shome, R., Tang, W., Song, C., Mitash, C., Kourtev, H., Yu, J., Boularias, A., & Bekris, K. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00984 · Cited by 5
“shown successful in the Amazon Picking Challenge [9]– [14] and attracted more interest.”
BackgroundSelf-citationCui, J., Shi, J., Liu, C., Bai, S., Shu, X., Zuo, X., Qian, Q., Xu, D., & Deng, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2024.129215 · Cited by 5
Luo, Q., Qiao, Y., & Yan, X. (2025) · Measurement · doi:10.1016/j.measurement.2025.119296 · Cited by 2
Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
Kriegler, A., Beleznai, C., & Gelautz, M. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02770-x · Cited by 6
“…11 ✓ ✗ ITODD-MV (Drost et al., 2017) 28 18 18 11 ✓ ✗ LM (Hinterstoisser et al., 2013) 15 3 3 2 ✗ ✓ LM-O (Brachmann et al., 2014) 8 2 2 1 ✗ ✓ RU-APC (Rennie et al., 2016) 14 8 1 1 ✗ ✓ T-LESS (Hodaˇn et al., 2017) 30 27 27 5 ✗ ✓ TUD-L (Hodaˇn et al., 2018) 3 0 0 0 ✗ ✓ TYO-L (Hodaˇn et al., 2018) 21…”
Satellite Pose Estimation via Only a Single Spatial Circle
Zhang, W., Xiao, P., & Li, J. (2022) · Information · doi:10.3390/info13020095 · Cited by 3
Chidambaram, S., Jain, R., Reddy, S. S., Unmesh, A., & Ramani, K. (2024) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4066180 · Cited by 2
“Other well-known works such as Linemod [41] utilize depth cameras such as Kinect [79] and available CAD models for mapping and pose estimation dataset generation.”
BackgroundMilano, F., Chung, J. J., Blum, H., Siegwart, R., & Ott, L. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801399 · Cited by 3
“…in recent evaluation benchmarks [15]–[17] provide this information, in practical real-world applications, obtaining an accurate, textured CAD reconstruction is often non-trivial, usually requiring manual design or specialized equipment for data collection or intensive post-processing [16], [18].”
Review on 6D Object Pose Estimation With the Focus on Indoor Scene Understanding
Nejatishahidin, N., & Fayyazsanavi, P. (2022) · Advances in Artificial Intelligence and Machine Learning · doi:10.54364/aaiml.2022.1141 · Cited by 2
Canonical Plane Segmentation Without Annotating Pixel-Level Object Regions for Image Registration
Yoneda, S., Irie, G., & Nishiyama, M. (2024) · IEEE Access · doi:10.1109/access.2024.3373463 · Cited by 2
“We evaluated the segmentation accuracy, pose estimation error, and recognition accuracy of the proposed network on a dataset that consisted of a mixture of three popular datasets for the picking process scenario: YCB dataset [30], APC dataset [31], and ARC dataset [32].”
MethodAD-LIB: Automated Library System
Sawant, D., & Patil, R. (2020) · Lecture notes in networks and systems · doi:10.1007/978-981-15-0146-3_59 · Cited by 2
Indoor Synthetic Data Generation: A Systematic ReviewPreprint
Schieber, H., Demir, K. C., Kleinbeck, C., Yang, S. H., & Roth, D. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4528507 · Cited by 2
Birk, A. (2025) · IEEE Access · doi:10.1109/access.2025.3614055 · Cited by 3
“Equipment encompasses in this context robot hardware [21], [23], [24], robotics simulations [25], [26], [27], and data-sets [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42].”
Monocular RGB 6D object pose estimation for augmented reality: a survey
Aguirrezabal, P., Aguinaga, I., & Álvarez-Gila, A. (2026) · Virtual Reality · doi:10.1007/s10055-026-01315-4 · Cited by 4
“The BOP benchmark later standardized these, along with the datasets listed in the Remaining BOP-Classic section (such as RU-APC (Rennie et al. 2016) and IC-MI (Tejani et al. 2014)), to form the set of 12 datasets known as “BOP-Classic”.”
Rosa, S., & Toscana, G. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.113 · Cited by 1
“showed only 32% accuracy in an APC-like scenario [14].”
BackgroundESKO6d - A Binocular and RGB-D Dataset of Stored Kitchen Objects with 6d Poses
Richter-Klug, J., Wellhausen, C., & Frese, U. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967937 · Cited by 3
“The Rutgers dataset targets the Amazon Picking Challenge [16] where objects are picked from warehouse shelves (24 objects, 10k images), with manually annotated poses.”
MethodInfluentialDeep Segmentation Network Without Mask Image Supervision for 2D Image Registration
Yoneda, S., Irie, G., Shibata, T., Nishiyama, M., & Iwai, Y. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-06381-7_16 · Cited by 1
“We evaluated the segmentation accuracy, recognition accuracy, and pose estimation error of our network on a dataset mixed with three popular datasets for the picking process scenario; YCB dataset [3], APC dataset [12], and ARC dataset [2].”
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration
Dang, Z., & Salzmann, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00827 · Cited by 4
“While much effort has been made to obtain real-world 3D ground truth [26, 23, 7, 25, 16, 31, 67, 48, 15, 58, 20], synthetic data generation [65, 66, 37, 61, 11] has emerged as an effective alternative source for supervision.”
BackgroundPerspective from International Robotics Competicion
Okada, K. (2017) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.35.9 · Cited by 1
6D Object Pose Estimation using Few-Shot Instance Segmentation and 3D Matching
Li, W., Sun, J., Luo, Y., & Wang, P. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9003070 · Cited by 1
“In order to evaluate the proposed method, we conduct experiments on LM-O (Linemod-Occluded) dataset [15] and RU-APC dataset [20].”
MethodYoneda, S., Ueno, K., Irie, G., Nishiyama, M., & Iwai, Y. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.11.005 · Cited by 1
“We evaluated object recognition accuracy and pose estimation error of our method by using three major datasets for product picking in warehouse scenarios: ARC dataset [3], YCB dataset [7], and APC dataset [22].”
[Retracted] Application of Embedded Intelligent Target Detection System in Basketball Movement Test
Zhang, C., & Wu, Y. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/5484706 · Cited by 1
“The only problem is the introduction of true shadows, which can be offset by increasing the brightness change threshold [25].”
BackgroundRetractedSaini, A., & Gupta, K. (2021) · Materials Today Proceedings · doi:10.1016/j.matpr.2020.12.1137 · Cited by 1
RetractedYoo, H. (2018) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2018.05.020
“As another 3D imaging technique, a color image and corresponding depth image have been very actively discussed [13-19].”
BackgroundMethodUeno, K., Nishiyama, M., & Iwai, Y. (2018) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.84.1041
Learning to Match Templates for Unseen Instance DetectionPreprint
Mercier, J. P., Garon, M., Giguère, P., & Lalonde, J. (2019) · arXiv (Cornell University) · Cited by 1
Template-based Unseen Instance DetectionPreprint
Mercier, J. P., Garon, M., Giguère, P., & Lalonde, J. (2019) · arXiv (Cornell University)
(2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2568418
Saqib, U. (2022) · VBN Forskningsportal (Aalborg Universitet) · doi:10.54337/aau528831183
Yuanlong, L. O. U., Fu, D., & Tian, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4856835
Sajjad, N., Price, A., Mirshams, M., & Salzmann, M. (2024) · Acta Astronautica · doi:10.1016/j.actaastro.2024.12.034 · Cited by 2
Martínez-Arellano, G., & Buck, M. G. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-86489-6_13
Object Pose Estimation Using Implicit Representation for Transparent Objects
Burde, V., Moroz, A., Zeman, V., & Burget, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91569-7_15 · Cited by 4
Algorithmic Perspectives on Active Object Recognition Systems: A Survey
Wang, Y., Li, J., Du, Z., Xue, T., & Zhang, T. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2025.9010096
Boerdijk, W., Durner, M., Sakagami, R., Lehner, P., & Triebel, R. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127593
“In [21] over 10,000 frames of 25 objects from the Amazon Picking Challenge with a camera mounted on a robotic arm were collected and annotated.”
Improving 6D Object Pose Estimation of Metallic Household and Industry Objects
Pöllabauer, T., Gasser, M., Wirth, T., Berkei, S., Knauthe, V., & Kuijper, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247314
ElMoaqet, H., Rashed, M., & Bakr, M. H. (2025) · Machines · doi:10.3390/machines13121126
“Previous studies in deep learning 6D pose estimation focused on datasets with the maximum depth not exceeding 1 m [17,33].”
6D Pose Estimation of Novel Objects: A Survey
Zang, J., Gao, T., Zhu, Z., & Jiang, X. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200385
A comprehensive review on advances in instance-level 6D object pose tracking
Wu, Y., Zhang, H., Vandewalle, P., Slaets, P., & Demeester, E. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104667 · Cited by 4
Desai, N., Sen, D., & Deb, S. (2026) · Intelligent Service Robotics · doi:10.1007/s11370-026-00711-8
“Widely used datasets such as YCB-Video [44], LineMOD-Occluded [45], HomebrewedDB, TUD-Light(TUD-L),ToyotaLight(TYOL)[54],andRutgersAPC [55] are designed for controlled or task-specific settings and therefore exhibit limited generalization to dense industrial bin-picking scenarios.”
Détection 3D pour la réalité mixte en maintenance industrielle
Roman, P. P. D. S. (2022) · theses.fr (ABES) · doi:10.70675/ca43c4cbz926fz42b0z94e8z2ac3cb283625
Alaya, T. L., de Azevedo, A. T., Ignácio, P. S. D. A., & Morini, C. (2026) · Gestão & Produção · doi:10.1590/1806-9649-2026v33e5124
Metadata
- Authors
- Rennie, C., Shome, R., Bekris, K. E., & De Souza, A. F.
- Affiliations
- Rutgers, The State University of New Jersey (US)
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2016-07
- Volume
- 1
- Issue
- 2
- Pages
- 1179-1185
- ISSN
- 2377-3766 (ISSN-L)
- 2377-3774
- OpenAlex
- W2221752211
- Cited by
- 182
- References
- 33
- Citations by year
- 2026: 6 · 2025: 15 · 2024: 20 · 2023: 17 · 2022: 17 · 2021: 24 · 2020: 14 · 2019: 24 · 2018: 17 · 2017: 12 · 2016: 16
- FWCI
- 19.32
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Robotics and Automation Letters (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rutgers University Community Repository (Rutgers University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Keywords
- RGB-D, 3D object pose estimation, object detection, depth sensing, cluttered scenes, low-light conditions, textureless objects, robotic manipulation
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.