Research map / 3D vision / 3D generation
You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image
Taoyue Wang, Xiang Zhang, Xiaotian Li, Huiyuan Yang, Lijun Yin
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 feature loss L_feat in training step 2 (ablation) | NVB-Face · NeRSemble novel-view | LPIPS: 0.24 -> 0.17 | Improved |
| add feature loss L_feat (ablation) | NVB-Face · NeRSemble novel-view | ID similarity: 0.57 -> 0.77 | Improved |
| add feature loss L_feat (ablation) | NVB-Face · NeRSemble novel-view | FID: 11.72 -> 5.67 | Improved |
| add feature loss L_feat (ablation) | NVB-Face · LFW-Test (qualitative) | multi-view consistency | Improved |
| one-stage NVB-Face instead of CodeFormer + two-stage novel-view synthesis | NVB-Face · NeRSemble novel-view | FID: 80.16 -> 5.67 (vs DiffPortrait3D) | Improved |
| one-stage NVB-Face vs two-stage baselines | NVB-Face · CelebA-Test single-view reconstruction | LPIPS: 0.49 vs 0.49-0.53 baselines; SSIM 0.63 vs 0.63 (TriPlaneNet) | Mixed |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.86)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.86)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.85)
- ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration (NeurIPS 2024 · similarity 0.84)
- OSDFace: One-Step Diffusion Model for Face Restoration (CVPR 2025 · similarity 0.84)
- Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering (NeurIPS 2024 · similarity 0.84)
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.
