Research map / 3D vision / 3D generation
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
Haofeng Liu, Yang Zhou, Ziheng Wang, Zhengbo Xu, Zhan Peng, Jie Ma, Jun Liang, Shengfeng He, Jing Li
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 late-stage source-video conditioning after scaffold (vs scaffold-only) (ablation) | MoCam · OpenVid 4D re-camera | imaging quality: 0.4807 -> 0.6932 | Improved |
| add late-stage source-video conditioning (vs scaffold-early with nothing later) (ablation) | MoCam · OpenVid 4D re-camera | imaging quality: 0.6172 -> 0.6932 | Improved |
| add late-stage source-video conditioning (vs scaffold-early) (ablation) | MoCam · OpenVid 4D re-camera | FVD-V: 273.19 -> 260.05 | Improved |
| switch from scaffold to source at T_switch instead of static both conditions (ablation) | MoCam · OpenVid 4D re-camera | RotErr / TransErr: 2.71 -> 1.36; 11.01 -> 5.12 | Improved |
| switch from scaffold to source instead of static both conditions (ablation) | MoCam · OpenVid 4D re-camera | FVD-V: 242.81 -> 260.05 | Hurt |
| use Wan2.1 backbone instead of Wan2.2 (ablation) | MoCam · OpenVid 4D re-camera | imaging quality: 0.6931 vs 0.6932 | No clear effect |
| use MoCam instead of GEN3C | single-view 3D reconstruction · OpenVid | FVD-V: 289.37 -> 255.16 | Improved |
| use MoCam instead of ViewCrafter | single-view 3D reconstruction · OpenVid | FVD-V: 308.24 -> 255.16 | Improved |
| use MoCam instead of GEN3C | video re-camera · iPhone dataset | FVD: 260.15 -> 180.35 | Improved |
| use MoCam instead of TrajCrafter | video re-camera · iPhone dataset | PSNR: 13.74 -> 14.60 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GEN3C — GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (CVPR 2025) · better on 7 of 8 shared results
- ViewCrafter — ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (TPAMI 2025) · 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
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.88)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.88)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.88)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.87)
- Dynamic View Synthesis as an Inverse Problem (NeurIPS 2025 · similarity 0.87)
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.87)
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.
