The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes
Open accessAbstract
Recent neural view synthesis methods have achieved impressive quality and realism, surpassing classical pipelines which rely on multi-view reconstruction. State-of-the-Art methods, such as NeRF [34], are designed to learn a single scene with a neural network and require dense multi-view inputs. Testing on a new scene requires re-training from scratch, which takes 2-3 days. In this work, we introduce Stereo Radiance Fields (SRF), a neural view synthesis approach that is trained end-to-end, generalizes to new scenes, and requires only sparse views at test time. The core idea is a neural architecture inspired by classical multi-view stereo methods, which estimates surface points by finding similar image regions in stereo images. In SRF, we predict color and density for each 3D point given an encoding of its stereo correspondence in the input images. The encoding is implicitly learned by an ensemble of pair-wise similarities – emulating classical stereo. Experiments show that SRF learns structure instead of over-fitting on a scene. We train on multiple scenes of the DTU dataset and generalize to new ones without re-training, requiring only 10 sparse and spread-out views as input. We show that 10-15 minutes of fine-tuning further improve the results, achieving significantly sharper, more detailed results than scene-specific models. The code, model, and videos are available – https://virtualhumans.mpi-inf.mpg.de/srf/.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
The 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
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
Scharstein, D., & Szeliski, R. (2002) · International Journal of Computer Vision · doi:10.1023/a:1014573219977 · Cited by 6,740 · cited 2×
“These approaches warp pixels to the desired target view via correspondences [39, 41, 49] or multiview 3D reconstruction [42, 43].”
BackgroundMethodStructure-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
Shade, J., Gortler, S., He, L.-W., & Szeliski, R. (1998) · Proceedings of the 25th annual conference on Computer graphics and interactive techniques - SIGGRAPH '98 · doi:10.1145/280814.280882 · Cited by 1,115 · cited 2×
“On the other end of the spectrum, popular classical image-based rendering techniques [46] use geometry [8, 29, 44, 45].”
Background
Cited by
TensoRF: Tensorial Radiance Fields
Chen, A., Xu, Z., Geiger, A., Yu, J., & Su, H. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19824-3_20 · Cited by 1,184
Depth-supervised NeRF: Fewer Views and Faster Training for Free
Deng, K., Liu, A., Zhu, J.-Y., & Ramanan, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01254 · Cited by 841
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
Niemeyer, M., Barron, J. T., Mildenhall, B., Sajjadi, M. S. M., Geiger, A., & Radwan, N. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00540 · Cited by 609
Neural Fields in Visual Computing and Beyond
Xie, Y., Takikawa, T., Saito, S., Litany, O., Yan, S., Khan, N., Tombari, F., Tompkin, J., sitzmann, V., & Sridhar, S. (2022) · Computer Graphics Forum · doi:10.1111/cgf.14505 · Cited by 484
PixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
Charatan, D., Li, S. L., Tagliasacchi, A., & Sitzmann, V. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01840 · Cited by 420
“Inspired by classical multi-view stereo, neural networks have also been combined with cost volumes to match features across views [5, 7, 18, 26].”
Method
Metadata
- Authors
- Chibane, J., Bansal, A., Lazova, V., & Pons-Moll, G.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 7907-7916
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3153167526
- Cited by
- 212
- References
- 7
- FWCI
- 13.17
- 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.