Research map / Video / Video segmentation and tracking
PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation
Chuanxin Song, Peixi Peng
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 PSNI noise initialization (ablation) | DepthCrafter baseline · PanoCARLA (avg of 3 settings) | AbsRel: 0.248 -> 0.228 | Improved |
| add CRTM cube temporal branch (ablation) | DepthCrafter baseline · PanoCARLA (avg of 3 settings) | AbsRel: 0.248 -> 0.208 | Improved |
| add CRTM on top of PSNI (ablation) | PVDepth · PanoCARLA (avg of 3 settings) | AbsRel: 0.228 -> 0.199 | Improved |
| extend baseline training from 20k to 40k steps (ablation) | DepthCrafter baseline · PanoCARLA (avg of 3 settings) | AbsRel: 0.248 -> 0.232 | Improved |
| anneal spherical noise instead of using it directly (ablation) | PSNI · PanoCARLA (avg of 3 settings) | AbsRel: 0.235 -> 0.228 | Improved |
| add residual normal noise to annealed noise (ablation) | PSNI + CRTM · PanoCARLA (avg of 3 settings) | AbsRel: 0.203 -> 0.199 | Improved |
| use projection layer rather than naive average fusion (ablation) | CRTM · PanoCARLA (avg of 3 settings) | AbsRel: 0.267 -> 0.214 | Improved |
| use projection layer rather than naive add fusion (ablation) | CRTM · PanoCARLA (avg of 3 settings) | AbsRel: 0.356 -> 0.214 | Improved |
| use cube features as key/value source instead of equi (ablation) | CRTM · PanoCARLA (avg of 3 settings) | AbsRel: 0.214 -> 0.208 | Improved |
| two-stage training instead of one-stage joint (ablation) | PVDepth · PanoCARLA (avg of 3 settings) | AbsRel: 0.221 -> 0.199 | Improved |
| freeze spatial layers in stage 2 (ablation) | PVDepth · PanoCARLA (avg of 3 settings) | AbsRel: 0.215 -> 0.199 | Improved |
| add PSNI under two-stage frozen protocol (ablation) | PVDepth · PanoCARLA (avg of 3 settings) | AbsRel: 0.204 -> 0.199 | Improved |
Closest papers by meaning
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.91)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.90)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.90)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.89)
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (CVPR 2025 · similarity 0.88)
- DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes (CVPR 2025 · similarity 0.88)
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.
