HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Benjamin Attal, Jia-Bin Huang, Christian Richardt, Michael Zollhöfer, Johannes Kopf, Matthew O'Toole, Changil Kim
Abstract
Figure 1. HyperReel: A novel 6-DoF video representation. HyperReel converts synchronized multi-view video streams into a high-fidelity, memory efficient scene representation that can be rendered from novel views and time steps at interactive rates. HyperReel's combination of high rendering quality, speed, and compactness sets it apart from existing 6-DoF video representations. The upper two rows show 6-DoF (i.e., varying viewpoint and viewing orientation) rendering of dynamic scenes [9, 48]; the lower two of static scenes [62, 65].
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers87
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingZeyu Yang, Hongye Yang, Zijie Pan, Li ZhangICLR 2024 · 529 citations
- 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingGuanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie et al.CVPR 2024 · 513 citations
- NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance FieldsLiangchen Song, Anpei Chen, Zhong Li, Zhang Chen et al.IEEE VR 2023 · 246 citations
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D GaussiansShenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli et al.CVPR 2024 · 175 citations
- Delicate Textured Mesh Recovery from NeRF via Adaptive Surface RefinementJiaxiang Tang, Hang Zhou, Xiaokang Chen, Tianshu Hu et al.ICCV 2023 · 162 citations
Builds on29
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
- Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields ReconstructionCheng Sun, Min Sun, Hwann-Tzong ChenCVPR 2022 · 859 citations
Related papers
- DynIBaR: Neural Dynamic Image-Based RenderingZhengqi Li, Qianqian Wang, Forrester Cole, Richard Tucker et al.CVPR 2023
- HumanRF: High-Fidelity Neural Radiance Fields for Humans in MotionMustafa Isik, Martin Rünz, Markos Georgopoulos, Taras Khakhulin et al.SIGGRAPH 2023 · 149 citations
- HUGS: Human Gaussian SplatsMuhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel et al.CVPR 2024
- GIFStream: 4D Gaussian-based Immersive Video with Feature StreamHao Li, Sicheng Li, Xiang Gao, Abudouaihati Batuer et al.CVPR 2025
- One-Shot Free-View Neural Talking-Head Synthesis for Video ConferencingTing-Chun Wang, Arun Mallya, Ming-Yu LiuCVPR 2021
