Research map / 3D vision / Face and shape
ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
Jiteng Mu, Shen Sang, Nuno Vasconcelos, Xiaolong Wang
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 category-level prior with 2-level canonical space (ActorsNeRF) over HumanNeRF | few-shot human NeRF · ZJU-MoCap Person 387, 5-shot | LPIPS (x10^3): 65.64 -> 46.06 | Improved |
| add category-level prior (ActorsNeRF) over HumanNeRF | few-shot human NeRF · AIST++ Person 16, 5-shot | PSNR: 24.37 -> 25.22 | Improved |
| increase number of support frames from 5 to 300 (ablation) | ActorsNeRF · ZJU-MoCap Person 387 | LPIPS (x10^3): 46.06 -> 36.18 | Improved |
| ActorsNeRF vs baselines at 300-shot on AIST++ | ActorsNeRF · AIST++ Person 20, 300-shot | PSNR: 26.00 (HumanNeRF) vs 25.78 | No clear effect |
| ActorsNeRF vs NeuralBody on PSNR at few shots | ActorsNeRF · ZJU-MoCap Person 393, 5-shot | PSNR: 27.54 (NeuralBody) vs 27.20 | Mixed |
| use ActorsNeRF in short-video setting with partial body coverage | ActorsNeRF · ZJU-MoCap Person 387, short-video | LPIPS (x10^3): 81.82 -> 50.88 | Improved |
| add deformation network (instance-level canonical space) (ablation) | ActorsNeRF · ZJU-MoCap 10-shot, Person 393 | LPIPS (x10^3): 44.13 -> 42.56 | Improved |
| add deformation network (ablation) | ActorsNeRF · ZJU-MoCap 10-shot, Person 387 | PSNR: 27.33 -> 27.15 | No clear effect |
| add pixel-aligned local features (ablation) | ActorsNeRF · ZJU-MoCap 10-shot, Person 393 | LPIPS (x10^3): 42.77 -> 42.56 | No clear effect |
| add SMPL local features (ablation) | ActorsNeRF · ZJU-MoCap 10-shot, Person 394 | LPIPS (x10^3): 37.13 -> 35.93 | Improved |
Later papers that compared with this method
1 later accepted paper reports ActorsNeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh (ICLR 2025 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 10 of 11 shared results
- NeuralBody — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 1 of 3 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
- MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images (TPAMI 2022 · similarity 0.88)
- HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses (CVPR 2024 · similarity 0.88)
- SHERF: Generalizable Human NeRF from a Single Image (ICCV 2023 · similarity 0.88)
- HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022 · similarity 0.87)
- HumanNeRF: Free-Viewpoint Rendering of Moving People From Monocular Video (CVPR 2022 · similarity 0.87)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.85)
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.
