Research map / 3D vision / Face and shape
MonoHuman: Animatable Human Neural Field From Monocular Video
Zhengming Yu, Wei Cheng, Xian Liu, Wayne Wu, Kwan-Yee Lin
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 the Shared Bidirectional Deformation consistency loss (ablation) | MonoHuman · ZJU-MoCap novel pose | LPIPS*: 32.39 -> 31.51 | Improved |
| Add the Shared Bidirectional Deformation consistency loss (ablation) | MonoHuman · ZJU-MoCap novel view | LPIPS*: 31.76 -> 30.92 | Improved |
| Add Forward Correspondence Search features (ablation) | MonoHuman · ZJU-MoCap novel view | LPIPS*: 31.39 -> 30.92 | Improved |
| Add Forward Correspondence Search features (ablation) | MonoHuman · ZJU-MoCap novel pose | LPIPS*: 31.80 -> 31.51 | Improved |
| Condition feature blend weights on view direction (ablation) | MonoHuman · Novel view synthesis | visual quality | Hurt |
| Use the full MonoHuman model rather than HumanNeRF | ZJU-MoCap novel view · ZJU-MoCap novel view | LPIPS*: 38.45 -> 30.92 | Improved |
| Use the full MonoHuman model rather than HumanNeRF | ZJU-MoCap novel pose · ZJU-MoCap novel pose | LPIPS*: 34.79 -> 31.51 | Improved |
| Increase training sequence length (ablation) | MonoHuman · ZJU-MoCap subject 394 novel view | PSNR: 27.52, 27.88, 27.77, 27.89 | Mixed |
Later papers that compared with this method
3 later accepted papers report MonoHuman as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses (CVPR 2024 · better on 8 of 8 shared results)
- GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh (CVPR 2024 · better on 4 of 4 shared results)
- MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition (ECCV 2024 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 6 of 6 shared results
- Neural Body — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 6 of 6 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 0.92)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (CVPR 2024 · similarity 0.90)
- Relightable and Animatable Neural Avatar from Sparse-View Video (CVPR 2024 · similarity 0.90)
- Pose Modulated Avatars from Video (ICLR 2024 · similarity 0.89)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.88)
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.
