Research map / 3D vision / Face and shape
CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation
Yicong Peng, Yichao Yan, Shengqi Liu, Yuhao Cheng, Shanyan Guan, Bowen Pan, Guangtao Zhai, Xiaokang Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use anti-aliasing MVC sampling instead of grid sampling (ablation) | CageNeRF · Animated Hulk | PSNR: 30.695 -> 35.280 | Improved |
| use anti-aliasing MVC sampling instead of grid sampling (ablation) | CageNeRF · Animated Hulk | SSIM: 0.916 -> 0.956 | Improved |
| use anti-aliasing MVC sampling instead of grid sampling (ablation) | CageNeRF · Animated Hulk | LPIPS: 0.0293 -> 0.0156 | Improved |
| use cage deformation instead of AniNeRF's learned blend-weight network for novel human poses | CageNeRF · Human3.6M average | PSNR: 23.76 -> 23.21 | Hurt |
| use cage deformation instead of AniNeRF's learned blend-weight network for novel human poses | CageNeRF · Human3.6M average | SSIM: 0.898 -> 0.882 | Hurt |
| CageNeRF vs Neural Human Rendering baseline | CageNeRF · Human3.6M average | PSNR: 21.47 -> 23.21 | Improved |
| CageNeRF vs Neural Textures baseline | CageNeRF · Human3.6M average | PSNR: 21.25 -> 23.21 | Improved |
| CageNeRF vs Neural Human Rendering baseline | CageNeRF · Human3.6M average | SSIM: 0.873 -> 0.882 | Improved |
| animate Hulk further from the starting frame (frame 1 to frame 47) | CageNeRF · Synthetic Hulk animation | PSNR: 36.434 -> 34.078 | Hurt |
| animate Hulk further from the starting frame (frame 1 to frame 47) | CageNeRF · Synthetic Hulk animation | LPIPS: 0.0126 -> 0.0188 | Hurt |
| animate Whale further from the starting frame (frame 1 to frame 100) | CageNeRF · Synthetic Whale animation | PSNR: 36.146 -> 35.085 | Mixed |
Closest papers by meaning
- Deforming Radiance Fields with Cages (ECCV 2022 · similarity 0.92)
- Neural Cages for Detail-Preserving 3D Deformations (CVPR 2020 · similarity 0.89)
- Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos (TPAMI 2024 · similarity 0.88)
- MoDA: Modeling Deformable 3D Objects from Casual Videos (IJCV 2024 · similarity 0.88)
- BANMo: Building Animatable 3D Neural Models From Many Casual Videos (CVPR 2022 · similarity 0.88)
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
