Research map / 3D vision / Face and shape
SelfRecon: Self Reconstruction Your Digital Avatar From Monocular Video
Boyi Jiang, Yang Hong, Hujun Bao, Juyong Zhang
Check 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 |
|---|---|---|---|
| replace VideoAvatar with SelfRecon | Clothed human reconstruction · Synthetic five sequences | Recon (cm): 1.66 -> 1.46 | Improved |
| replace VideoAvatar with SelfRecon | Clothed human reconstruction · Synthetic five sequences | GT (cm): 1.86 -> 1.48 | Improved |
| replace VideoAvatar with SelfRecon | Clothed human reconstruction · Synthetic five sequences | Chamfer (cm): 1.76 -> 1.47 | Improved |
| add color loss to mask-only optimization (ablation) | SelfRecon · Qualitative examples | Geometry detail | Improved |
| add predicted-normal loss to mask and color losses (ablation) | SelfRecon · Qualitative examples | Geometry detail | Improved |
| remove adaptive weights from normal loss (ablation) | SelfRecon · Qualitative examples | Geometry plausibility | Hurt |
| use adaptive weights for normal loss (ablation) | SelfRecon · Qualitative examples | Geometry plausibility | Improved |
Later papers that compared with this method
6 later accepted papers report SelfRecon as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · better on 4 of 4 shared results)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · better on 12 of 12 shared results)
- ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV 2024 · better on 4 of 4 shared results)
- HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024 · better on 4 of 4 shared results)
- Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video (CVPR 2023 · better on 5 of 5 shared results)
- Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023 · better on 4 of 4 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
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.88)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (CVPR 2024 · similarity 0.87)
- MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos (AAAI 2026 · similarity 0.87)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.87)
- REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos (CVPR 2023 · similarity 0.86)
- HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction (AAAI 2024 · 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.
