“BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes” – ACM SIGGRAPH HISTORY ARCHIVES

“BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes”

  • ©

Conference:


Type(s):


Title:

    BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes

Presenter(s)/Author(s):



Abstract:


    BoostMVSNeRFs revolutionizes 3D scene visualization by improving the quality of large-scale MVS-based NeRFs. This innovative technique combines multiple cost volumes with 3D visibility scores to enhance novel view synthesis without additional training. Compatible with current frameworks, it sets new 3D reconstruction and visualization standards, offering significant quality and efficiency improvements.

References:


    [1]
    Kara-Ali Aliev, Artem Sevastopolsky, Maria Kolos, Dmitry Ulyanov, and Victor Lempitsky. 2020. Neural point-based graphics. In ECCV.

    [2]
    Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In ICCV.

    [3]
    Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2022. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In CVPR.

    [4]
    Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2023. Zip-NeRF: Anti-aliased grid-based neural radiance fields. In ICCV.

    [5]
    Mark Boss, Raphael Braun, Varun Jampani, Jonathan T Barron, Ce Liu, and Hendrik Lensch. 2021. Nerd: Neural reflectance decomposition from image collections. In ICCV.

    [6]
    Ang Cao, Chris Rockwell, and Justin Johnson. 2022. Fwd: Real-time novel view synthesis with forward warping and depth. In CVPR.

    [7]
    Gaurav Chaurasia, Sylvain Duchene, Olga Sorkine-Hornung, and George Drettakis. 2013. Depth synthesis and local warps for plausible image-based navigation. ACM TOG (2013).

    [8]
    Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, and Hao Su. 2022. Tensorf: Tensorial radiance fields. In ECCV.

    [9]
    Anpei Chen, Zexiang Xu, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, and Hao Su. 2021. Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In ICCV.

    [10]
    Rui Chen, Songfang Han, Jing Xu, and Hao Su. 2019. Point-based multi-view stereo network. In ICCV.

    [11]
    Yuedong Chen, Haofei Xu, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, and Jianfei Cai. 2023. Explicit Correspondence Matching for Generalizable Neural Radiance Fields. arXiv preprint arXiv:2304.12294 (2023).

    [12]
    Bo-Yu Cheng, Wei-Chen Chiu, and Yu-Lun Liu. 2024. Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields. In AAAI.

    [13]
    Julian Chibane, Aayush Bansal, Verica Lazova, and Gerard Pons-Moll. 2021. Stereo radiance fields (srf): Learning view synthesis for sparse views of novel scenes. In CVPR.

    [14]
    Angela Dai, Angel X Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, and Matthias Nie?ner. 2017. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In CVPR.

    [15]
    Paul E Debevec, Camillo J Taylor, and Jitendra Malik. 2023. Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. In Seminal Graphics Papers: Pushing the Boundaries, Volume 2.

    [16]
    Kangle Deng, Andrew Liu, Jun-Yan Zhu, and Deva Ramanan. 2022. Depth-supervised nerf: Fewer views and faster training for free. In CVPR.

    [17]
    Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, and Federico Tombari. 2019. Peeking behind objects: Layered depth prediction from a single image. Pattern Recognition Letters (2019).

    [18]
    John Flynn, Michael Broxton, Paul Debevec, Matthew DuVall, Graham Fyffe, Ryan Overbeck, Noah Snavely, and Richard Tucker. 2019. Deepview: View synthesis with learned gradient descent. In CVPR.

    [19]
    John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. 2016. Deepstereo: Learning to predict new views from the world?s imagery. In CVPR.

    [20]
    Yiming Gao, Yan-Pei Cao, and Ying Shan. 2023. SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes. In CVPR.

    [21]
    Jonathan Shade Steven Gortler, Li-wei He, Richard Szeliski, 1998. Layered depth images. In SIGGRAPH.

    [22]
    Xiaodong Gu, Zhiwen Fan, Siyu Zhu, Zuozhuo Dai, Feitong Tan, and Ping Tan. 2020. Cascade cost volume for high-resolution multi-view stereo and stereo matching. In CVPR.

    [23]
    Peter Hedman, Pratul P Srinivasan, Ben Mildenhall, Jonathan T Barron, and Paul Debevec. 2021. Baking neural radiance fields for real-time view synthesis. In ICCV.

    [24]
    Ajay Jain, Matthew Tancik, and Pieter Abbeel. 2021. Putting nerf on a diet: Semantically consistent few-shot view synthesis. In ICCV.

    [25]
    Yue Jiang, Dantong Ji, Zhizhong Han, and Matthias Zwicker. 2020. Sdfdiff: Differentiable rendering of signed distance fields for 3d shape optimization. In CVPR.

    [26]
    Mohammad Mahdi Johari, Yann Lepoittevin, and Fran?ois Fleuret. 2022. Geonerf: Generalizing nerf with geometry priors. In CVPR.

    [27]
    Nima Khademi Kalantari, Ting-Chun Wang, and Ravi Ramamoorthi. 2016. Learning-based view synthesis for light field cameras. ACM TOG (2016).

    [28]
    Mijeong Kim, Seonguk Seo, and Bohyung Han. 2022. Infonerf: Ray entropy minimization for few-shot neural volume rendering. In CVPR.

    [29]
    Tianye Li, Mira Slavcheva, Michael Zollhoefer, Simon Green, Christoph Lassner, Changil Kim, Tanner Schmidt, Steven Lovegrove, Michael Goesele, Richard Newcombe, 2022. Neural 3d video synthesis from multi-view video. In CVPR.

    [30]
    Zhengqi Li, Wenqi Xian, Abe Davis, and Noah Snavely. 2020. Crowdsampling the plenoptic function. In ECCV.

    [31]
    Haotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei Zhou. 2023b. Im4d: High-fidelity and real-time novel view synthesis for dynamic scenes. arXiv preprint arXiv:2310.08585 (2023).

    [32]
    Haotong Lin, Sida Peng, Zhen Xu, Yunzhi Yan, Qing Shuai, Hujun Bao, and Xiaowei Zhou. 2022. Efficient neural radiance fields for interactive free-viewpoint video. In SIGGRAPH Asia.

    [33]
    Kai-En Lin, Yen-Chen Lin, Wei-Sheng Lai, Tsung-Yi Lin, Yi-Chang Shih, and Ravi Ramamoorthi. 2023a. Vision transformer for nerf-based view synthesis from a single input image. In WACV.

    [34]
    Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Hyeongwoo Kim, Florian Bernard, Marc Habermann, Wenping Wang, and Christian Theobalt. 2019. Neural rendering and reenactment of human actor videos. ACM TOG (2019).

    [35]
    Yuan Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, and Wenping Wang. 2022. Neural rays for occlusion-aware image-based rendering. In CVPR.

    [36]
    Yu-Lun Liu, Chen Gao, Andreas Meuleman, Hung-Yu Tseng, Ayush Saraf, Changil Kim, Yung-Yu Chuang, Johannes Kopf, and Jia-Bin Huang. 2023. Robust dynamic radiance fields. In CVPR.

    [37]
    Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, and Yaser Sheikh. 2019. Neural volumes: Learning dynamic renderable volumes from images. ACM TOG (2019).

    [38]
    Stephen Lombardi, Tomas Simon, Gabriel Schwartz, Michael Zollhoefer, Yaser Sheikh, and Jason Saragih. 2021. Mixture of volumetric primitives for efficient neural rendering. ACM TOG (2021).

    [39]
    Andreas Meuleman, Yu-Lun Liu, Chen Gao, Jia-Bin Huang, Changil Kim, Min H Kim, and Johannes Kopf. 2023. Progressively optimized local radiance fields for robust view synthesis. In CVPR.

    [40]
    Ben Mildenhall, Pratul P Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar. 2019. Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM TOG (2019).

    [41]
    Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.

    [42]
    Thomas M?ller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM TOG (2022).

    [43]
    Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas M?ller, and Sanja Fidler. 2022. Extracting triangular 3d models, materials, and lighting from images. In CVPR.

    [44]
    George L Nemhauser, Laurence A Wolsey, and Marshall L Fisher. 1978. An analysis of approximations for maximizing submodular set functions?I. Mathematical programming (1978).

    [45]
    Michael Niemeyer, Jonathan T Barron, Ben Mildenhall, Mehdi SM Sajjadi, Andreas Geiger, and Noha Radwan. 2022. Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs. In CVPR.

    [46]
    Michael Oechsle, Songyou Peng, and Andreas Geiger. 2021. Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In ICCV.

    [47]
    Keunhong Park, Utkarsh Sinha, Jonathan T Barron, Sofien Bouaziz, Dan B Goldman, Steven M Seitz, and Ricardo Martin-Brualla. 2021. Nerfies: Deformable neural radiance fields. In ICCV.

    [48]
    Eric Penner and Li Zhang. 2017. Soft 3d reconstruction for view synthesis. ACM TOG (2017).

    [49]
    Hanspeter Pfister, Matthias Zwicker, Jeroen Van Baar, and Markus Gross. 2000. Surfels: Surface elements as rendering primitives. In Proceedings of the 27th annual conference on Computer graphics and interactive techniques.

    [50]
    Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. 2021. D-nerf: Neural radiance fields for dynamic scenes. In CVPR.

    [51]
    Gernot Riegler and Vladlen Koltun. 2020. Free view synthesis. In ECCV.

    [52]
    Barbara Roessle, Jonathan T Barron, Ben Mildenhall, Pratul P Srinivasan, and Matthias Nie?ner. 2022. Dense depth priors for neural radiance fields from sparse input views. In CVPR.

    [53]
    Seunghyeon Seo, Donghoon Han, Yeonjin Chang, and Nojun Kwak. 2023. MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputs. In CVPR.

    [54]
    Yue Shi, Dingyi Rong, Bingbing Ni, Chang Chen, and Wenjun Zhang. 2022. Garf: Geometry-aware generalized neural radiance field. arXiv preprint arXiv:2212.02280 (2022).

    [55]
    Meng-Li Shih, Shih-Yang Su, Johannes Kopf, and Jia-Bin Huang. 2020. 3d photography using context-aware layered depth inpainting. In CVPR.

    [56]
    Vincent Sitzmann, Justus Thies, Felix Heide, Matthias Nie?ner, Gordon Wetzstein, and Michael Zollhofer. 2019. Deepvoxels: Learning persistent 3d feature embeddings. In CVPR.

    [57]
    Nagabhushan Somraj and Rajiv Soundararajan. 2023. ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields. (2023).

    [58]
    Pratul P Srinivasan, Richard Tucker, Jonathan T Barron, Ravi Ramamoorthi, Ren Ng, and Noah Snavely. 2019. Pushing the boundaries of view extrapolation with multiplane images. In CVPR.

    [59]
    Cheng Sun, Min Sun, and Hwann-Tzong Chen. 2022. Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In CVPR.

    [60]
    Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul P Srinivasan, Jonathan T Barron, and Henrik Kretzschmar. 2022. Block-nerf: Scalable large scene neural view synthesis. In CVPR.

    [61]
    Justus Thies, Michael Zollh?fer, and Matthias Nie?ner. 2019. Deferred neural rendering: Image synthesis using neural textures. ACM TOG (2019).

    [62]
    Alex Trevithick and Bo Yang. 2021. Grf: Learning a general radiance field for 3d representation and rendering. In ICCV.

    [63]
    Richard Tucker and Noah Snavely. 2020. Single-view view synthesis with multiplane images. In CVPR.

    [64]
    Shubham Tulsiani, Richard Tucker, and Noah Snavely. 2018. Layer-structured 3d scene inference via view synthesis. In ECCV.

    [65]
    Mikaela Angelina Uy, Ricardo Martin-Brualla, Leonidas Guibas, and Ke Li. 2023. SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates. In CVPR.

    [66]
    Michael Waechter, Nils Moehrle, and Michael Goesele. 2014. Let there be color! Large-scale texturing of 3D reconstructions. In ECCV.

    [67]
    Guangcong Wang, Zhaoxi Chen, Chen Change Loy, and Ziwei Liu. 2023a. Sparsenerf: Distilling depth ranking for few-shot novel view synthesis. In ICCV.

    [68]
    Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021a. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. In NeurIPS.

    [69]
    Peng Wang, Yuan Liu, Zhaoxi Chen, Lingjie Liu, Ziwei Liu, Taku Komura, Christian Theobalt, and Wenping Wang. 2023b. F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories. In CVPR.

    [70]
    Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P Srinivasan, Howard Zhou, Jonathan T Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. 2021b. Ibrnet: Learning multi-view image-based rendering. In CVPR

    [71]
    Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE TIP (2004).

    [72]
    Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, and Jie Zhou. 2021. Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo. In ICCV.

    [73]
    Suttisak Wizadwongsa, Pakkapon Phongthawee, Jiraphon Yenphraphai, and Supasorn Suwajanakorn. 2021. Nex: Real-time view synthesis with neural basis expansion. In CVPR.

    [74]
    Daniel N Wood, Daniel I Azuma, Ken Aldinger, Brian Curless, Tom Duchamp, David H Salesin, and Werner Stuetzle. 2023. Surface light fields for 3D photography. In Seminal Graphics Papers: Pushing the Boundaries, Volume 2.

    [75]
    Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P Srinivasan, Dor Verbin, Jonathan T Barron, Ben Poole, 2023. ReconFusion: 3D Reconstruction with Diffusion Priors. arXiv preprint arXiv:2312.02981 (2023).

    [76]
    Jamie Wynn and Daniyar Turmukhambetov. 2023. Diffusionerf: Regularizing neural radiance fields with denoising diffusion models. In CVPR.

    [77]
    Wenqi Xian, Jia-Bin Huang, Johannes Kopf, and Changil Kim. 2021. Space-time neural irradiance fields for free-viewpoint video. In CVPR.

    [78]
    Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, and Ulrich Neumann. 2022. Point-nerf: Point-based neural radiance fields. In CVPR.

    [79]
    Jiawei Yang, Marco Pavone, and Yue Wang. 2023. FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization. In CVPR.

    [80]
    Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, and Long Quan. 2018. Mvsnet: Depth inference for unstructured multi-view stereo. In ECCV.

    [81]
    Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, and Long Quan. 2019. Recurrent mvsnet for high-resolution multi-view stereo depth inference. In CVPR.

    [82]
    Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. In NeurIPS.

    [83]
    Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Basri Ronen, and Yaron Lipman. 2020. Multiview neural surface reconstruction by disentangling geometry and appearance. In NeurIPS.

    [84]
    Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. 2022. Plenoxels: Radiance fields without neural networks. In CVPR.

    [85]
    Alex Yu, Ruilong Li, Matthew Tancik, Hao Li, Ren Ng, and Angjoo Kanazawa. 2021a. Plenoctrees for real-time rendering of neural radiance fields. In ICCV.

    [86]
    Alex Yu, Vickie Ye, Matthew Tancik, and Angjoo Kanazawa. 2021b. pixelnerf: Neural radiance fields from one or few images. In CVPR.

    [87]
    Zehao Yu and Shenghua Gao. 2020. Fast-mvsnet: Sparse-to-dense multi-view stereo with learned propagation and gauss-newton refinement. In CVPR.

    [88]
    Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, and Noah Snavely. 2021a. Physg: Inverse rendering with spherical gaussians for physics-based material editing and relighting. In CVPR.

    [89]
    Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. 2020. Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020).

    [90]
    Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR.

    [91]
    Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su, and Zexiang Xu. 2022. Nerfusion: Fusing radiance fields for large-scale scene reconstruction. In CVPR.

    [92]
    Xiuming Zhang, Pratul P Srinivasan, Boyang Deng, Paul Debevec, William T Freeman, and Jonathan T Barron. 2021b. Nerfactor: Neural factorization of shape and reflectance under an unknown illumination. ACM TOG (2021).

    [93]
    Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo magnification: Learning view synthesis using multiplane images. In SIGGRAPH.

    [94]
    Bingfan Zhu, Yanchao Yang, Xulong Wang, Youyi Zheng, and Leonidas Guibas. 2023. Vdn-nerf: Resolving shape-radiance ambiguity via view-dependence normalization. In CVPR.


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org