Research map / Video / Video generation
Generative View Stitching
Chonghyuk Song, Michal Stary, Boyuan Chen, George Kopanas, Vincent Sitzmann
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 |
|---|---|---|---|
| replace autoregressive sampling with GVS parallel stitching | DFoT video model · predefined camera trajectories | F2FC and collision avoidance: Straight line F2FC 0.138 -> 0.080; Circle 1-loop CA 0.625 -> 0 | Improved |
| replace StochSync with GVS | DFoT video model · predefined camera trajectories | F2FC: Staircase circuit 0.179 -> 0.129 | Improved |
| increase stochasticity eta from 0 to 1 without Omni Guidance (ablation) | vanilla GVS · Straight line | F2FC: F2FC 0.153 -> 0.061; IQ 0.537 -> 0.422 | Mixed |
| add Omni Guidance at partial stochasticity eta=0.9 (ablation) | GVS · Straight line | F2FC: 0.084 -> 0.080 (IQ 0.458 -> 0.615) | Improved |
| add Omni Guidance at eta=0 (ablation) | GVS · Straight line | F2FC: 0.153 -> 0.138 | Improved |
| add Omni Guidance at maximum stochasticity eta=1 (ablation) | GVS · Straight line | F2FC: 0.061 -> 0.071 | Hurt |
| add loop closing via cyclic conditioning (ablation) | GVS · Panorama 1-loop | LRC: 0.950 -> 0.201 (no Omni Guidance) | Improved |
| add Omni Guidance without loop closing (ablation) | GVS · Panorama 1-loop | LRC: 0.950 -> 0.962 | No clear effect |
| add Omni Guidance with loop closing active (ablation) | GVS · Panorama 1-loop | LRC: 0.201 -> 0.141 | Improved |
| add Omni Guidance without loop closing (ablation) | GVS · Panorama 1-loop | imaging quality IQ: 0.442 -> 0.554 | Improved |
Closest papers by meaning
- NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer (ICLR 2025 · similarity 0.88)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.88)
- StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation (CVPR 2025 · similarity 0.88)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.88)
- GenFusion: Closing the Loop between Reconstruction and Generation via Videos (CVPR 2025 · similarity 0.87)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (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.
