Research map / 3D vision / Face and shape
DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars
David Svitov, Dmitrii Gudkov, Renat Bashirov, Victor Lempitsky
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 |
|---|---|---|---|
| use both RGB and neural texture channels instead of either alone (ablation) | DINAR · Ablation (15 AzurePeople images) | PSNR: 22,8041 (RGB) / 23,0935 (neural) -> 24,1041 | Improved |
| add DDPM texture inpainting (ablation) | DINAR · Ablation (15 AzurePeople images) | PSNR: 24,1041 -> 24,8510 | Improved |
| add DDPM texture inpainting (ablation) | DINAR · Ablation (15 AzurePeople images) | LPIPS: 0,1005 -> 0,0904 | Improved |
| add occlusion detector (ablation) | DINAR · Ablation (15 AzurePeople images) | PSNR: 24,8510 -> 24,8619 | No clear effect |
| add RGB texture fine-tuning at inference (ablation) | DINAR · Ablation (15 AzurePeople images) | PSNR: 24,8619 -> 24,9758 | Improved |
| use DINAR instead of StylePeople for back-view quality | one-shot avatars · SnapshotPeople (novel view) | KID: 0.0530 -> 0.0133 | Improved |
| DINAR versus PIFu on same-view reconstruction | DINAR · SnapshotPeople (same view) | PSNR: PIFu 26.2828 vs DINAR 24.4182 | Hurt |
| DINAR versus PIFu on THuman2.0 same view | DINAR · THuman2.0 (same view) | PSNR: PIFu 28,2686 vs DINAR 22,8671 | 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.
- ARCH++ — ARCH++: Animation-Ready Clothed Human Reconstruction Revisited (ICCV 2021) · 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
- DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars (CVPR 2024 · similarity 0.87)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.87)
- Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models (NeurIPS 2024 · similarity 0.86)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.86)
- CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025 · similarity 0.86)
- Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion (CVPR 2025 · 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.
