Research map / 3D vision / 3D generation
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Wangbo Yu, Jinbo Xing, Li Yuan, Wenbo Hu, Xiaoyu Li, Zhipeng Huang, Xiangjun Gao, Tien‐Tsin Wong, Ying Shan, Yonghong Tian
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 point cloud renders instead of Plucker coordinates as pose condition (ablation) | ViewCrafter · zero-shot NVS (320x512) | PSNR: 17.51 -> 20.25 | Improved |
| use point cloud renders instead of Plucker coordinates as pose condition (ablation) | ViewCrafter · zero-shot NVS (320x512) | R_dist: 2.688 -> 0.552 | Improved |
| use point cloud renders instead of Plucker coordinates as pose condition (ablation) | ViewCrafter · zero-shot NVS (320x512) | T_dist: 2.570 -> 0.983 | Improved |
| train temporal layers in addition to spatial layers (ablation) | ViewCrafter · zero-shot NVS | PSNR: 18.82 -> 19.52 | Improved |
| progressive training (320x512 then 576x1024) instead of direct high-res (ablation) | ViewCrafter · zero-shot NVS | PSNR: 18.55 -> 19.52 | Improved |
| infer 25 frames instead of 16 (ablation) | ViewCrafter · zero-shot NVS | PSNR: 19.07 -> 19.52 | Improved |
| infer 25 frames instead of 16 (ablation) | ViewCrafter · zero-shot NVS | FID: 38.43 -> 37.77 | Improved |
| progressive training instead of direct high-res (ablation) | ViewCrafter · zero-shot NVS | FID: 41.01 -> 37.77 | Improved |
Later papers that compared with this method
22 later accepted papers report ViewCrafter as a baseline in their results tables; 22 of them report a better number on most of the results they share with it.
- EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis (ICLR 2026 · better on 6 of 6 shared results)
- Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation (ICLR 2026 · better on 5 of 5 shared results)
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (NeurIPS 2026 · better on 3 of 3 shared results)
- Perceptual 3D Simulation With Physical World Modeling (CVPR 2026 · better on 3 of 3 shared results)
- Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context (CVPR 2026 · better on 3 of 3 shared results)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · better on 2 of 2 shared results)
- UniGeo: Unifying Geometric Constraints for Camera-Controllable Image Editing via Video Priors (ECCV 2026 · better on 2 of 2 shared results)
- MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics (ECCV 2026 · better on 1 of 1 shared result)
14 more not listed.
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.
- DNGaussian — DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization (CVPR 2024) · 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
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.92)
- NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer (ICLR 2025 · similarity 0.91)
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.90)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.90)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.90)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.90)
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.
