Research map / 3D vision / Face and shape
MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images
Xiangjun Gao, Jiaolong Yang, Jongyoo Kim, Sida Peng, Zicheng Liu, Xin Tong
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 |
|---|---|---|---|
| add canonical space (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 23.34 -> 25.63 | Improved |
| add canonical space (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 21.77 -> 23.92 | Improved |
| add attention-based multiview feature fusion (vs average pooling) (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 22.05 -> 25.63 | Improved |
| add attention-based multiview feature fusion (vs average pooling) (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 21.18 -> 23.92 | Improved |
| use two attention MLPs (geometry and color) instead of a single attention (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 25.29 -> 25.63 | Improved |
| use two attention MLPs (geometry and color) instead of a single attention (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 23.63 -> 23.92 | Improved |
| add shape loss (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 25.16 -> 25.63 | Improved |
| add shape loss (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 23.57 -> 23.92 | Improved |
| add smoothness loss (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 25.38 -> 25.63 | Improved |
| add smoothness loss (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 23.64 -> 23.92 | Improved |
| increase number of input views from 3 to 12 (ablation) | MPS-NeRF · THuman novel view synthesis | PSNR: 25.63 -> 27.77 | Improved |
| increase number of input views from 3 to 12 (ablation) | MPS-NeRF · THuman novel pose synthesis | PSNR: 23.92 -> 24.56 | Improved |
Later papers that compared with this method
1 later accepted paper reports MPS-NeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- SHERF: Generalizable Human NeRF from a Single Image (ICCV 2023 · better on 9 of 9 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuralBody — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 6 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neural Capture of Animatable 3D Human from Monocular Video (ECCV 2022 · similarity 0.91)
- Learning Neural Volumetric Representations of Dynamic Humans in Minutes (CVPR 2023 · similarity 0.90)
- Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis (ICCV 2021 · similarity 0.90)
- SHERF: Generalizable Human NeRF from a Single Image (ICCV 2023 · similarity 0.90)
- GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images (CVPR 2023 · similarity 0.90)
- PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF (AAAI 2024 · similarity 0.89)
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.
