Research map / 3D vision / 3D generation
Rendering Humans from Object-Occluded Monocular Videos
Tiange Xiang, Adam Sun, Jiajun Wu, Ehsan Adeli, Li Fei-Fei
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 |
|---|---|---|---|
| replace HumanNeRF with OccNeRF | HumanNeRF · ZJU-MoCap 387 (simulated occlusion) | PSNR_vis: 9.551 -> 13.27 | Improved |
| replace HumanNeRF with OccNeRF | HumanNeRF · ZJU-MoCap 386 (simulated occlusion) | PSNR_vis: 9.491 -> 13.44 | Improved |
| replace HumanNeRF with OccNeRF | HumanNeRF · ZJU-MoCap 393 (simulated occlusion) | SSIM_full: 0.9476 -> 0.9489 | Improved |
| replace HumanNeRF with OccNeRF | HumanNeRF · OcMotion severe real occlusion | PSNR_vis: 11.40 -> 14.95 | Improved |
| replace HumanNeRF with OccNeRF | HumanNeRF · OcMotion mild real occlusion | PSNR_vis: 13.38 -> 14.56 | Improved |
| add visibility attention to surface aggregation (ablation) | OccNeRF · ZJU-MoCap | rendering quality | Improved |
| add completeness loss (ablation) | OccNeRF · ZJU-MoCap | geometry completeness | Improved |
| add surface-based rendering on top of hash grid encoding (ablation) | OccNeRF · ZJU-MoCap | rendering quality | 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.
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 20 of 20 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
- Rendering Humans behind Occlusions (TPAMI 2025 · similarity 0.94)
- OccFusion: Rendering Occluded Humans with Generative Diffusion Priors (NeurIPS 2024 · similarity 0.91)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.89)
- HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024 · similarity 0.88)
- O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model (AAAI 2024 · similarity 0.86)
- DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery (CVPR 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.
