Research map / 3D vision / Face and shape
Human Interaction-Aware 3D Reconstruction from a Single Image
Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon, Jason Park, Se Young Chun
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 |
|---|---|---|---|
| train HUG-MVD on both group and instance data instead of group-only (ablation) | HUG-MVD · MultiHuman ablation | CD (cm): 4.564 -> 4.316 | Improved |
| train HUG-MVD on both group and instance data instead of group-only (ablation) | HUG-MVD · MultiHuman ablation | PSNR: 15.641 -> 16.454 | Improved |
| train HUG-MVD on both data sources instead of instance-only (ablation) | HUG-MVD · MultiHuman ablation | CD (cm): 4.645 -> 4.316 | Improved |
| train HUG-MVD on both data sources instead of instance-only (ablation) | HUG-MVD · MultiHuman ablation | PSNR: 15.840 -> 16.454 | Improved |
| add instance-to-group latent composition (ablation) | HUG-MVD · MultiHuman ablation | CD (cm): 4.646 -> 4.316 | Improved |
| add instance-to-group latent composition (ablation) | HUG-MVD · MultiHuman ablation | PSNR: 16.198 -> 16.454 | Improved |
| add group-level normal supervision to instance-only (ablation) | HUG-GR · MultiHuman ablation | CD (cm): 4.642 -> 4.316 | Improved |
| add instance-level normal supervision to group-only (ablation) | HUG-GR · MultiHuman ablation | CD (cm): 4.620 -> 4.316 | Improved |
| add instance-level normal supervision to group-only (ablation) | HUG-GR · MultiHuman ablation | PSNR: 16.169 -> 16.454 | Improved |
| add interpenetration loss (ablation) | HUG-GR · MultiHuman (qualitative) | mesh interpenetration | Improved |
| add visibility loss (ablation) | HUG-GR · MultiHuman (qualitative) | contact surface quality | Improved |
| add adaptive-region specific optimization (ablation) | HUG-GR · MultiHuman (qualitative) | hand detail quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SIFU — SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024) · better on 10 of 10 shared results
- SiTH — SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024) · better on 2 of 2 shared results
- PSHuman — PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025) · better on 1 of 1 shared result
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
- ContactField: Implicit Field Representation for Multi-Person Interaction Geometry (NeurIPS 2024 · similarity 0.91)
- Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation (CVPR 2024 · similarity 0.88)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.88)
- InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025 · similarity 0.88)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.88)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (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.
