Research map / 3D vision / Face and shape
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
Arindam Dutta, Meng Zheng, Zhongpai Gao, Benjamin Planche, Anwesa Choudhuri, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu
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 estimated 3D pose conditioning (ControlNet) to the multiview diffusion model (ablation) | CHROME · Occluded THuman2.0 | PSNR: 20.40 -> 20.54 | Improved |
| add estimated 3D pose conditioning (ablation) | CHROME · Occluded THuman2.0 | SSIM: .8833 -> .9098 | Improved |
| use pose-controlled multiview diffusion plus reconstruction instead of inpainting then SIFU (ablation) | CHROME · Occluded THuman2.0 | PSNR: 16.27 -> 20.54 | Improved |
| increase occlusion size from 25% to 75% (ablation) | CHROME · Occluded THuman2.0 | PSNR: 19.51 -> 19.06 | Hurt |
| increase occlusion size from 25% to 75% (ablation) | SIFU · Occluded THuman2.0 | PSNR: 15.39 -> 14.04 | Hurt |
| use two input views instead of one | CHROME · Occluded THuman2.0 | PSNR: 20.54 -> 24.32 | Improved |
| increase stereo angle from 45 to 135 degrees (ablation) | CHROME · Occluded THuman2.0 stereo | PSNR: 24.32 -> 24.78 | No clear effect |
| apply CHROME on clean unoccluded images versus SIFU with SMPL and 3D supervision | CHROME · Clean THuman2.0 | PSNR: 22.10 -> 20.80 | Hurt |
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.
- SIFU — SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024) · better on 3 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
- 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)
- Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field (CVPR 2024 · similarity 0.88)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.88)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (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.
