Research map / 3D vision / Face and shape
iVS-Net: Learning Human View Synthesis from Internet Videos
Junting Dong, Qi Fang, Tianshuo Yang, Qing Shuai, Chengyu Qiao, Sida Peng
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 video self-supervision with a paired frame from the same video (ablation) | iVS-Net · ZJU-MoCap | PSNR: 17.86 -> 24.67 | Improved |
| add perceptual (LPIPS) loss to L2+L1 (ablation) | iVS-Net · ZJU-MoCap | LPIPS: 0.251 -> 0.230 | Improved |
| add adversarial loss (ablation) | iVS-Net · ZJU-MoCap | LPIPS: 0.230 -> 0.196 | Improved |
| add adversarial loss (ablation) | iVS-Net · ZJU-MoCap | PSNR: 24.72 -> 24.67 | No clear effect |
| train on Internet monocular videos instead of multi-view studio images | iVS-Net vs NHP · ZJU-MoCap (unseen subjects) | PSNR: 18.71 -> 24.08 | Improved |
| train pixelNeRF/NHP on monocular videos without video self-supervision | pixelNeRF, NHP · ZJU-MoCap | PSNR: 24.67 (iVS-Net) vs 18.63 / 17.51 | Hurt |
Closest papers by meaning
- Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021 · similarity 0.88)
- Implicit Neural Representations With Structured Latent Codes for Human Body Modeling (TPAMI 2023 · similarity 0.88)
- Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video (ECCV 2020 · similarity 0.87)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.86)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.85)
- OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation (CVPR 2025 · similarity 0.85)
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.
