Research map / 3D vision / Face and shape
REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos
Lingteng Qiu, Guanying Chen, Jiapeng Zhou, Mutian Xu, Junle Wang, Xiaoguang Han
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 joint dynamic curve and surface optimization with progressive co-evolution | REC-MV · Female1, Female3, Male1, and Male2 synthetic sequences | CD (cm): Female1: 1.810 -> 1.804; Female3: 1.924 -> 1.641; Male1: 2.005 -> 1.736; Male2: 2.865 -> 1.812 | Improved |
| Use joint dynamic curve and surface optimization with progressive co-evolution | REC-MV · Female1, Female3, Male1, and Male2 synthetic sequences | CCV: Female1: 3.782 -> 0.597; Female3: 4.322 -> 1.064; Male1: 6.794 -> 0.484; Male2: 3.579 -> 0.433 | Improved |
| Use implicit garment SDF and SMPL surfaces for z-buffer visibility checks instead of normal direction alone (ablation) | REC-MV · Monocular video garment reconstruction | curve visibility / reconstruction quality | Improved |
| Add curve slope regularization (ablation) | REC-MV · Monocular video garment reconstruction | curve fitting quality | Improved |
| Add on-surface regularization for feature curves (ablation) | REC-MV · Monocular video garment reconstruction | curve fitting accuracy | Improved |
| Add curve-guided implicit consistency loss (ablation) | REC-MV · Monocular video garment reconstruction | surface geometry quality | Improved |
Later papers that compared with this method
1 later accepted paper reports REC-MV as a baseline in their results tables; 1 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)
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
- NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction (ICCV 2025 · similarity 0.92)
- Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates (TPAMI 2026 · similarity 0.91)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.89)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.89)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.88)
- Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models (CVPR 2024 · 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.
