Research map / Video / Video generation
S$^{2}$VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
Peng Dai, Feitong Tan, Qiangeng Xu, Yihua Huang, David Futschik, Ruofei Du, Sean Fanello, Yinda Zhang, Xiaojuan Qi
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 frame matrix (ablation) | S2VG · stereoscopic generation | CLIP similarity: 95.81 -> 96.44 | Improved |
| add frame matrix (ablation) | S2VG · stereoscopic generation | FVD: 614 -> 599 | Hurt |
| add disocclusion boundary re-injection (ablation) | S2VG · stereoscopic generation | aesthetic score: 5.18 -> 5.27 | Improved |
| add disocclusion boundary re-injection (ablation) | S2VG · stereoscopic generation | FVD: 699 -> 599 | Improved |
| add data processing (cracks, isolated points) (ablation) | S2VG · stereoscopic generation | FVD: 733 -> 599 | Improved |
| add data processing (ablation) | S2VG · stereoscopic generation | DOVER: 0.576 -> 0.584 | Improved |
| use 6 cameras instead of 4 (ablation) | S2VG · stereoscopic generation | FVD: 579 -> 599 | Hurt |
| use 6 cameras instead of 4 (ablation) | S2VG · stereoscopic generation | DOVER: 0.565 -> 0.584 | Improved |
| replace Zeroscope with Wan 2.1 backbone | S2VG · stereo generation | DOVER: 0.584 -> 0.566 | Hurt |
| replace Zeroscope with Wan 2.1 backbone | S2VG · stereo generation | FVD: 599 -> 595 | No clear effect |
| use S2VG instead of Free4D | S2VG · spatial generation | FVD: 1129 -> 518 | Improved |
| use S2VG instead of Deep3D | S2VG · human study stereo effect | Stereo effect: 2.27 -> 5.24 | 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.
- ProPainter — ProPainter: Improving Propagation and Transformer for Video Inpainting (ICCV 2023) · better on 4 of 4 shared results
- Free4D — Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency (ICCV 2025) · better on 2 of 2 shared results
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
- SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix (ICLR 2025 · similarity 0.96)
- SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input (CVPR 2025 · similarity 0.88)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Imagine360: Immersive 360 Video Generation from Perspective Anchor (NeurIPS 2025 · similarity 0.87)
- GenFusion: Closing the Loop between Reconstruction and Generation via Videos (CVPR 2025 · similarity 0.87)
- GeoVideo: Introducing Geometric Regularization into Video Generation Model (NeurIPS 2025 · 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.
