Research map / 3D vision / Face and shape
TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video
Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, Minh Vo
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 self-supervised fine-tuning on the real video (ablation) | MeshRef · Synthetic videos, mesh (normal images) | silhouette IoU: 0.940 -> 0.941 | Improved |
| add self-supervised fine-tuning on the real video (ablation) | MeshRef · Synthetic videos, mesh (normal images) | normal RMSE: 0.186 -> 0.173 | Improved |
| add self-supervised fine-tuning on the real video (ablation) | MeshRef · Synthetic videos, mesh (normal images) | MS-SSIM: 0.857 -> 0.870 | Improved |
| use normal image instead of RGB image as MeshRef input (ablation) | MeshRef · Synthetic videos, mesh (normal images) | silhouette IoU: 0.928 -> 0.941 | Improved |
| use normal image instead of RGB image as MeshRef input (ablation) | MeshRef · Synthetic videos, mesh (normal images) | normal RMSE: 0.190 -> 0.173 | Improved |
| use normal image instead of RGB image as MeshRef input (ablation) | MeshRef · Synthetic videos, mesh (normal images) | MS-SSIM: 0.852 -> 0.870 | Improved |
| add VGG features to the normal image encoding (ablation) | MeshRef · Synthetic videos, mesh (normal images) | normal RMSE: 0.185 -> 0.173 | Improved |
| add VGG features to the normal image encoding (ablation) | MeshRef · Synthetic videos, mesh (normal images) | silhouette IoU: 0.932 -> 0.941 | Improved |
| add deformation propagation loss (ablation) | MeshRef · Synthetic videos, mesh (normal images) | normal RMSE: 0.174 -> 0.173 | No clear effect |
| add deformation propagation loss (ablation) | MeshRef · Synthetic videos, mesh (normal images) | MS-SSIM: 0.869 -> 0.870 | No clear effect |
| use CNN-refined albedo key-frame texture instead of TNA texture stack | TexGen · Synthetic videos, albedo texture | RMSE: 0.146 -> 0.119 | Improved |
| use TexMesh instead of Tex2Shape variant for mesh | TexMesh · Synthetic videos, mesh (normal images) | normal RMSE: 0.192 -> 0.173 | Improved |
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.
- DeepHuman — DeepHuman: 3D Human Reconstruction From a Single Image (ICCV 2019) · better on 3 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
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.87)
- Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation (CVPR 2025 · similarity 0.86)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.86)
- TexVocab: Texture Vocabulary-conditioned Human Avatars (CVPR 2024 · similarity 0.86)
- DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation (NeurIPS 2024 · similarity 0.86)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · 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.
