Research map / Video / Video generation
Robust Pose Transfer With Dynamic Details Using Neural Video Rendering
Yang-Tian Sun, Haozhi Huang, Xuan Wang, Yu‐Kun Lai, Wei Liu, Lin Gao
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 D2G-Net dynamic details generation network (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | SSIM: 0.913 -> 0.933 | Improved |
| add D2G-Net dynamic details generation network (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | PSNR: 36.35 -> 37.44 | Improved |
| add hybrid texture instead of RGB texture (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | SSIM: 0.921 -> 0.933 | Improved |
| add hybrid texture instead of RGB texture (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | PSNR: 36.87 -> 37.44 | Improved |
| add pose label condition to D2G-Net (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | SSIM: 0.918 -> 0.933 | Improved |
| add pose label condition to D2G-Net (ablation) | neural video rendering with hybrid texture · Ablation, short monocular videos | PSNR: 36.62 -> 37.44 | Improved |
| use explicit 3D neural rendering with hybrid texture instead of direct image translation (EDN) | pose transfer · Short monocular videos | SSIM: 0.911 -> 0.933 | Improved |
| use implicit dynamic details instead of explicit dynamic texture of DTL | neural rendering · Short monocular videos | PSNR: 37.2 -> 37.44 | Improved |
| use hybrid texture and D2G-Net instead of static texture (TNA) | neural rendering · Short monocular videos | E_temp: 0.46 -> 0.41 | Improved |
| use hybrid texture and D2G-Net instead of static texture (TNA) | neural rendering · Short monocular videos | FID: 55.68 -> 53.49 | Improved |
Closest papers by meaning
- High-Fidelity Neural Human Motion Transfer From Monocular Video (CVPR 2021 · similarity 0.90)
- Pose-Guided Human Animation From a Single Image in the Wild (CVPR 2021 · similarity 0.90)
- Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos (ICCV 2025 · similarity 0.89)
- Learning Neural Volumetric Representations of Dynamic Humans in Minutes (CVPR 2023 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling (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.
