Neural Scene Graphs for Dynamic Scenes
Open accessThe DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images. However, existing methods are restricted to learning efficient representations of static scenes that encode all scene objects into a single neural network, and they lack the ability to represent dynamic scenes and decompose scenes into individual objects. In this work, we present the first neural rendering method that represents multi-object dynamic scenes as scene graphs. We propose a learned scene graph representation, which encodes object transformations and radiance, allowing us to efficiently render novel arrangements and views of the scene. To this end, we learn implicitly encoded scenes, combined with a jointly learned latent representation to describe similar objects with a single implicit function. We assess the proposed method on synthetic and real automotive data, validating that our approach learns dynamic scenes – only by observing a video of this scene – and allows for rendering novel photo-realistic views of novel scene compositions with unseen sets of objects at unseen poses.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
The unreasonable effectiveness of deep features as a perceptual metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · arXiv · doi:10.48550/arxiv.1801.03924 · Cited by 24,812
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 9×
“Table 1: We report PSNR, SSIM, LPIPS, tOF and tLP results on scenes from KITTI [11] for SRN [32], NeRF [22], a modified NeRF for temporal scenes and our neural scene graph method.”
BackgroundMethodInfluentialThe Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Structure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433 · cited 1×
“Classical methods rely on sequential reconstructions and rendering pipelines that first recover a compact scene representation, such as a pointcloud or textured meshes using multi-view stereo [1, 12, 28, 29], which is then used to render novel views using efficient direct or global illumination rendering methods.”
MethodMultiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253 · cited 3×
“For PSNR and SSIM, higher is better; for LPIPS lower is better.”
MethodNeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_24 · Cited by 5,351
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
Park, J. J., Florence, P., Straub, J., Newcombe, R., & Lovegrove, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00025 · Cited by 3,422
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
Shi, S., Wang, X., & Li, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00086 · Cited by 3,093
Cited by
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
Barron, J. T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., & Srinivasan, P. P. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00580 · Cited by 1,921
Block-NeRF: Scalable Large Scene Neural View Synthesis
Tancik, M., Casser, V., Yan, X., Pradhan, S., Mildenhall, B. P., Srinivasan, P., Barron, J. T., & Kretzschmar, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00807 · Cited by 781
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
Liao, Y., Xie, J., & Geiger, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3179507 · Cited by 736
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
Reiser, C., Peng, S., Liao, Y., & Geiger, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01407 · Cited by 668
Baking Neural Radiance Fields for Real-Time View Synthesis
Hedman, P., Srinivasan, P. P., Mildenhall, B., Barron, J. T., & Debevec, P. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00582 · Cited by 451
HexPlane: A Fast Representation for Dynamic Scenes
Cao, A., & Johnson, J. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00021 · Cited by 435
Tewari, A., Thies, J., Mildenhall, B., Srinivasan, P., Tretschk, E., Yifan, W., Lassner, C., Sitzmann, V., Martin‐Brualla, R., Lombardi, S., et al. (2022) · Computer Graphics Forum · doi:10.1111/cgf.14507 · Cited by 339
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions
Haque, A., Tancik, M., Efros, A. A., Holynski, A., & Kanazawa, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01808 · Cited by 314
Rematas, K., Liu, A., Srinivasan, P., Barron, J., Tagliasacchi, A., Funkhouser, T., & Ferrari, V. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01259 · Cited by 277
DONeRF: Towards Real‐Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks
Neff, T., Stadlbauer, P., Parger, M., Kurz, A., Mueller, J. H., Chaitanya, C. R. A., Kaplanyan, A., & Steinberger, M. (2021) · Computer Graphics Forum · doi:10.1111/cgf.14340 · Cited by 256
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
Song, L., Chen, A., Li, Z., Chen, Z., Chen, L., Yuan, J., Xu, Y., & Geiger, A. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3247082 · Cited by 254
DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
Zhou, X., Lin, Z., Shan, X., Wang, Y., Sun, D., & Yang, M.-H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02044 · Cited by 248
“We demonstrate the qualitative comparison results with our main competitors NSG [11], EmerNeRF [21] and 3DGS [4] on driving scenes reconstruction of nuScenes. method 3DGS [4], our method achieves higher rendering quality with comparable rendering speed.”
InfluentialUniSim: A Neural Closed-Loop Sensor Simulator
Yang, Z., Chen, Y., Wang, J., Manivasagam, S., Ma, W.-C., Yang, A. J., & Urtasun, R. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00140 · Cited by 170
“Composing neural feature fields: Inspired by works that composite solid objects [23, 56] into a scene, we first transform object-centric neural fields of the foreground actors to world coordinates with the desired poses (e.”
BackgroundMethodInfluential3D Object Detection from Images for Autonomous Driving: A Survey
Ma, X., Ouyang, W., Simonelli, A., & Ricci, E. (2022) · arXiv · doi:10.48550/arxiv.2202.02980 · Cited by 147
DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
Zhao, G., Ni, C., Wang, X., Zhu, Z., Zhang, X., Wang, Y., Huang, G., Chen, X., Wang, B., Zhang, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2410.13571 · Cited by 41
Scene Graph Contrastive Learning for Embodied Navigation
Singh, K. P., Salvador, J., Weihs, L., & Kembhavi, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00999 · Cited by 23
“Building rich scene representations has been an active area of research including approaches to build graphs from static images [16, 47, 50, 75, 76, 81] and ones that contain temporal information from videos [15, 38, 48, 54, 60, 65].”
Background
Metadata
- Authors
- Ost, J., Mannan, F., Thuerey, N., Knodt, J., & Heide, F.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 2855-2864
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3108625339
- Cited by
- 263
- References
- 36
- FWCI
- 32.27
- Type
- conference paper
- Language
- en
- Open access
- green
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.