ReconFusion: 3D Reconstruction with Diffusion Priors
Open accessThe DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.
Abstract
3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets, which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets, including forward-facing and 360-degree scenes, demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches. Please see our project page at reconfusion.github. io.
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
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
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302 · cited 4×
“The trained diffusion model produces plausible single images for novel camera poses, but generated images are often inconsistent for different poses or random seeds.”
InfluentialLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
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
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712 · cited 2×
“With the recent success of diffusion models for image generation [20, 51], researchers have applied diffusion models to the task of novel view synthesis — modeling the distribution of unseen views given observations from known views [15, 29, 63].”
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Kerbl, B., Kopanas, G., Leimkuehler, T., & Drettakis, G. (2023) · ACM Transactions on Graphics · doi:10.1145/3592433 · Cited by 6,025
NeRF: 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
Self-citationDenoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507
ShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
Barron, J. T., Mildenhall, B., Verbin, D., Srinivasan, P. P., & Hedman, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00539 · Cited by 1,935 · cited 3×
“6, our test set performance is consistently better than Zip-NeRF, indicating that our diffusion prior can serve as an effective drop-in regularizer across a range of capture settings.”
Self-citationShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T. A., Guibas, L. J., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2023) · doi:10.5281/zenodo.10089705 · Cited by 1,623
pixelNeRF: Neural Radiance Fields from One or Few Images
Yu, A., Ye, V., Tancik, M., & Kanazawa, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00455 · Cited by 1,560
Local light field fusion: practical view synthesis with prescriptive sampling guidelines
Mildenhall, B., Srinivasan, P. P., Ortiz-Cayon, R., Kalantari, N. K., Ramamoorthi, R., Ng, R., & Kar, A. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322980 · Cited by 1,175
Self-citationZip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Barron, J. T., Mildenhall, B., Verbin, D., Srinivasan, P. P., & Hedman, P. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01804 · Cited by 1,139
Self-citationEfficient Geometry-aware 3D Generative Adversarial Networks
Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., de Mello, S., Gallo, O., Guibas, L., Tremblay, J., Khamis, S., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01565 · Cited by 1,093 · cited 1×
“Earlier works addressing this problem primarily leverage Generative Adversarial Networks (GANs) [3, 4, 12–14, 18, 33, 34, 46, 73].”
MVDream: Multi-view Diffusion for 3D Generation
Shi, Y., Wang, P., Ye, J., Long, M., Li, K., & Yang, X. (2023) · International Conference on Learning Representations · doi:10.48550/arxiv.2308.16512 · Cited by 958
Two deterministic half-quadratic regularization algorithms for computed imaging
Charbonnier, P., Blanc-Feraud, L., Aubert, G., & Barlaud, M. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413553 · Cited by 879 · cited 1×
“Evaluation Dataset We evaluate our method on scenes from multiple datasets with 3, 6 and 9 input views, which include in-distribution datasets (CO3D [39] and RealEstate10K [71]) and out-of-distribution datasets (LLFF [31], DTU [23] and mip-NeRF 360 [1]).”
Magic3D: High-Resolution Text-to-3D Content Creation
Lin, C.-H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.-Y., & Lin, T.-Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00037 · Cited by 857 · cited 1×
“Lifting 2D diffusion models for 3D generation Given the limited amount of 3D data available for training, recent works have attempted to leverage 2D diffusion models to generate 3D assets from a text prompt [28, 37, 59, 61] or an input image [29, 48].”
Zero-1-to-3: Zero-shot One Image to 3D Object
Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00853 · Cited by 841
Self-citationDepth-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 · cited 3×
“DS-NeRF [10] utilizes sparse depth outputs from Structure-from-Motion (SfM) as supervision.”
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
Chen, A., Xu, Z., Zhao, F., Zhang, X., Xiang, F., Yu, J., & Su, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01386 · Cited by 797
Stereo magnification: learning view synthesis using multiplane images
Zhou, T., Tucker, R., Flynn, J., Fyffe, G., & Snavely, N. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201323 · Cited by 776
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
Niemeyer, M., & Geiger, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01129 · Cited by 731
Objaverse: A Universe of Annotated 3D Objects
Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsanit, K., Kembhavi, A., & Farhadi, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01263 · Cited by 725 · cited 3×
“4, we ablate two aspects of our diffusion model: the use of pretrained diffusion model weights (PT) and conditioning signal.”
IBRNet: Learning Multi-View Image-Based Rendering
Wang, Q., Wang, Z., Genova, K., Srinivasan, P., Zhou, H., Barron, J. T., Martin-Brualla, R., Snavely, N., & Funkhouser, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00466 · Cited by 725 · cited 1×
“These networks leverage large collections of posed multiview data across many scenes [8, 11, 19, 21, 44, 55, 57, 60, 67, 71].”
Self-citationpi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
Chan, E. R., Monteiro, M., Kellnhofer, P., Wu, J., & Wetzstein, G. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00574 · Cited by 689 · cited 1×
“Earlier works addressing this problem primarily leverage Generative Adversarial Networks (GANs) [3, 4, 12–14, 18, 33, 34, 46, 73].”
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Liu, Y., Lin, C., Zeng, Z., Long, X., Liu, L., Komura, T., & Wang, W. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2309.03453 · Cited by 669 · cited 2×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
BackgroundRegNeRF: 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
Self-citationDeep Stereo: Learning to Predict New Views from the World's Imagery
Flynn, J., Neulander, I., Philbin, J., & Snavely, N. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.595 · Cited by 574
Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
Jain, A., Tancik, M., & Abbeel, P. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00583 · Cited by 463 · cited 1×
“Few-view NeRF Minimizing NeRF’s need for dense capture is crucial for democratizing 3D capture, and has motivated many works [10, 16, 22, 27, 35, 41, 47, 49, 50, 58, 62, 64, 65, 69].”
Dense Depth Priors for Neural Radiance Fields from Sparse Input Views
Roessle, B., Barron, J. T., Mildenhall, B., Srinivasan, P. P., & Niebner, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01255 · Cited by 358 · cited 3×
“DDP-NeRF [41] further uses a CNN to obtain dense depth supervision from sparse inputs.”
Self-citationCommon Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction
Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., & Novotny, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01072 · Cited by 352 · cited 7×
“GeNVS [5] and SparseFusion [16] train on real-world multiview data [39] and further incorporate 3D geometry priors by conditioning on rendered features [52, 67].”
InfluentialSelf-citationScore Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Wang, H., Du, X., Li, J., Yeh, R. A., & Shakhnarovich, G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01214 · Cited by 343 · cited 1×
“Lifting 2D diffusion models for 3D generation Given the limited amount of 3D data available for training, recent works have attempted to leverage 2D diffusion models to generate 3D assets from a text prompt [28, 37, 59, 61] or an input image [29, 48].”
MVImgNet: A Large-scale Dataset of Multi-view Images
Yu, X., Xu, M., Zhang, Y., Liu, H., Ye, C., Wu, Y., Yan, Z., Zhu, C., Xiong, Z., Liang, T., et al. (2023) · 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/cvpr52729.2023.00883 · Cited by 330 · cited 3×
“…[67] for conditioning (similar to GeNVS [5]) to allow for any number of input images and provide more precise pose conditioning, and fine-tunes a pretrained image diffusion model on real-world multiview datasets [39, 68, 71], which combined facilitates few-view reconstruction on arbitrary scenes.”
Single-View View Synthesis With Multiplane Images
Tucker, R., & Snavely, N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00063 · Cited by 324
FreeNeRF: Improving Few-Shot Neural Rendering with Free Frequency Regularization
Yang, J., Pavone, M., & Wang, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00798 · Cited by 316
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 · cited 1×
“Please refer to the supplementary materials for more implementation details.”
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
Wang, G., Chen, Z., Loy, C. C., & Liu, Z. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00832 · Cited by 266 · cited 4×
“Many methods aim to reduce the reliance on dense captures by developing heuristic low-level regularizers based on re-constructed depth [10, 16, 41], visibility [27, 49], appearance [35, 64], or image-space frequencies [65].”
Influential3D Shape Induction from 2D Views of Multiple Objects
Gadelha, M., Maji, S., & Wang, R. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00053 · Cited by 260
State of the Art on Diffusion Models for Visual Computing
Po, R., Yifan, W., Golyanik, V., Aberman, K., Barron, J. T., Bermano, A. H., Chan, E. R., Dekel, T., Holynski, A., Kanazawa, A., et al. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15063 · Cited by 251 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
BackgroundSelf-citationVisual Object Networks: Image Generation with Disentangled 3D RepresentationPreprint
Zhu, J.-Y., Zhang, Z., Zhang, C., Wu, J., Torralba, A. B., Tenenbaum, J., & Freeman, B. (2018) · neural information processing systems · doi:10.48550/arxiv.1812.02725 · Cited by 246
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
Gao, J., Shen, T., Wang, Z., Chen, W., Yin, K., Li, D., Litany, O., Gojčič, Ž., & Fidler, S. (2022) · neural information processing systems · doi:10.52202/068431-2308 · Cited by 233
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
Yu, Z., Peng, S., Niemeyer, M., Sattler, T., & Geiger, A. (2022) · neural information processing systems · doi:10.52202/068431-1814 · Cited by 203
GRF: Learning a General Radiance Field for 3D Representation and Rendering
Trevithick, A., & Yang, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01490 · Cited by 202 · cited 1×
“These networks leverage large collections of posed multiview data across many scenes [8, 11, 19, 21, 44, 55, 57, 60, 67, 71].”
DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models
Wynn, J., & Turmukhambetov, D. (2023) · 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/cvpr52729.2023.00407 · Cited by 198
Escaping Plato’s Cave: 3D Shape From Adversarial Rendering
Henzler, P., Mitra, N., & Ritschel, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01008 · Cited by 194 · cited 1×
“Earlier works addressing this problem primarily leverage Generative Adversarial Networks (GANs) [3, 4, 12–14, 18, 33, 34, 46, 73].”
Self-citationHoloGAN: Unsupervised Learning of 3D Representations From Natural Images
Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., & Yang, Y.-L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00255 · Cited by 178 · cited 1×
“Earlier works addressing this problem primarily leverage Generative Adversarial Networks (GANs) [3, 4, 12–14, 18, 33, 34, 46, 73].”
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
Schwarz, K., Sauer, A., Niemeyer, M., Liao, Y., & Geiger, A. (2022) · neural information processing systems · doi:10.52202/068431-2464 · Cited by 172
SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction
Zhou, Z., & Tulsiani, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01211 · Cited by 171
Consistent View Synthesis with Pose-Guided Diffusion Models
Tseng, H.-Y., Li, Q., Kim, C., Alsisan, S., Huang, J., & Kopf, J. (2023) · 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/cvpr52729.2023.01609 · Cited by 167 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
Generalizable Patch-Based Neural Rendering
Suhail, M., Esteves, C., Sigal, L., & Makadia, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19824-3_10 · Cited by 165
ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
Sargent, K., Li, Z., Shah, T. H., Herrmann, C., Yu, H.-X., Zhang, Y., Chan, E. R., Lagun, D., Fei-Fei, L., Sun, D., et al. (2024) · 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/cvpr52733.2024.00900 · Cited by 162
HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images
Karnewar, A., Vedaldi, A., Novotný, D., & Mitra, N. J. (2023) · 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/cvpr52729.2023.01767 · Cited by 158 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data
Szymanowicz, S., Rupprecht, C., & Vedaldi, A. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00814 · Cited by 152 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
BackgroundSajjadi, M. S. M., Meyer, H., Pot, E., Bergmann, U., Greff, K., Radwan, N., Vora, S., Lucic, M., Duckworth, D., Dosovitskiy, A., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00613 · Cited by 143 · cited 1×
“These networks leverage large collections of posed multiview data across many scenes [8, 11, 19, 21, 44, 55, 57, 60, 67, 71].”
Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation
Wang, Z., Lu, C., Wang, Y., Bao, F., Li, C., Su, H., & Zhu, J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-0368 · Cited by 143
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Tewari, A., Yin, T., Cazenavette, G., Rezchikov, S., Tenenbaum, J. B., Durand, F., Freeman, B., & Sitzmann, V. (2023) · neural information processing systems · doi:10.52202/075280-0542 · Cited by 127
Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs
Warburg, F., Weber, E., Tancik, M., Holynski, A., & Kanazawa, A. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01661 · Cited by 115 · cited 1×
“Few-view NeRF Minimizing NeRF’s need for dense capture is crucial for democratizing 3D capture, and has motivated many works [10, 16, 22, 27, 35, 41, 47, 49, 50, 58, 62, 64, 65, 69].”
ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields
Somraj, N., & Soundararajan, R. (2023) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3588432.3591539 · Cited by 81 · cited 2×
“Many methods aim to reduce the reliance on dense captures by developing heuristic low-level regularizers based on re-constructed depth [10, 16, 41], visibility [27, 49], appearance [35, 64], or image-space frequencies [65].”
BackgroundMethodNeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Irshad, M. Z., Zakharov, S., Liu, K., Guizilini, V., Kollar, T., Gaidon, A., Kira, Z., & Ambruş, R. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00843 · Cited by 77 · cited 1×
“These networks leverage large collections of posed multiview data across many scenes [8, 11, 19, 21, 44, 55, 57, 60, 67, 71].”
BackgroundSCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
Uy, M. A., Martin-Brualla, R., Guibas, L. J., & Li, K. (2023) · 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/cvpr52729.2023.01585 · Cited by 58 · cited 1×
“Few-view NeRF Minimizing NeRF’s need for dense capture is crucial for democratizing 3D capture, and has motivated many works [10, 16, 22, 27, 35, 41, 47, 49, 50, 58, 62, 64, 65, 69].”
BackgroundHoloFusion: Towards Photo-realistic 3D Generative Modeling
Karnewar, A., Mitra, N. J., Vedaldi, A., & Novotný, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02100 · Cited by 45 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image
Ren, X., & Wang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00355 · Cited by 43 · cited 1×
“More recent works use diffusion models, following their immense success on image generation [5, 15, 16, 24, 25, 29, 30, 36, 40, 48, 53, 54, 56, 66].”
GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
Roessle, B., Muller, N. E., Porzi, L., Bulò, S. R., Kontschieder, P., & Nießner, M. (2023) · ACM Transactions on Graphics · doi:10.1145/3618402 · Cited by 39 · cited 1×
“GANeRF [42] trains a generator network to improve NeRF renderings and an image discriminator network to provide feedback that can be used to improve the reconstruction in a multiview-consistent manner.”
MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputs
Seo, S., Han, D., Chang, Y., & Kwak, N. (2023) · 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/cvpr52729.2023.01979 · Cited by 39 · cited 1×
“Few-view NeRF Minimizing NeRF’s need for dense capture is crucial for democratizing 3D capture, and has motivated many works [10, 16, 22, 27, 35, 41, 47, 49, 50, 58, 62, 64, 65, 69].”
SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions
Somraj, N., Karanayil, A., & Soundararajan, R. (2023) · SIGGRAPH Asia Conference Papers · doi:10.1145/3610548.3618188 · Cited by 31 · cited 3×
“Baselines For evaluation datasets, we compare against the state-of-the-art dense-view NeRF model Zip-NeRF [2] (which is also the reconstruction pipeline used in our model), and state-of-the-art few-view NeRF regularization methods including DiffusioNeRF [64], FreeNeRF [65], and SimpleNeRF [50].”
BackgroundMethod
Cited by
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-view Images
Chen, Y., Xu, H., Zheng, C., Zhuang, B., Pollefeys, M., Geiger, A., Cham, T.-J., & Cai, J. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72664-4_21 · Cited by 231
“…., Scene Representation Networks (SRN) [34], Neural Radiance Fields (NeRF) [24] and Light Filed Networks (LFN) [33], these methods are still not satisfactory for practical applications due to expensive per-scene optimization [26,39,43], high memory cost [3,18,44] and slow rendering speed [40,49].”
BackgroundDriveDreamer4D: 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
Metadata
- Authors
- Wu, R., Mildenhall, B., Henzler, P., Park, K., Gao, R., Watson, D., Srinivasan, P. P., Verbin, D., Barron, J. T., Poole, B., & Hołyński, A.
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 21551-21561
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402667896
- Cited by
- 190
- References
- 67
- FWCI
- 54.28
- 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.