Research map / Video / Video segmentation and tracking
PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
Shilin Yan, Xiaohao Xu, Renrui Zhang, Lingyi Hong, wenchao chen, Wenqiang Zhang, Wei Zhang
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 PSC attention (left-right boundary stitching) to the VOS transformer (ablation) | Ours-Base · PanoVOS validation | J&F: 72.8 -> 74.0 | Improved |
| add PSC attention (ablation) | Ours-Large · PanoVOS validation | J&F: 74.8 -> 77.9 | Improved |
| add PSC attention (ablation) | Ours-Large · PanoVOS test | J&F: 59.5 -> 59.9 | No clear effect |
| replace cross-attention with PSC attention (ablation) | Ours-Base · PanoVOS test | J&F: 54.8 -> 56.8 | Improved |
| add boundary stitching mechanism with p=2 (ablation) | Ours-Large · PanoVOS validation | J&F: 73.7 -> 77.9 | Improved |
| vary stitching hyperparameter p from 2 to 5, 10 or 15 (ablation) | Ours-Large · PanoVOS validation | J&F: 77.9 -> 74.2 (p=5) | Hurt |
| deploy planar-video VOS models on panoramic videos without re-training | off-the-shelf VOS models · PanoVOS validation | J&F: AOTB YouTube-VOS 83.5 -> 70.5 | Hurt |
| train on larger VOS data (YouTube-VOS, BL30K) | off-the-shelf VOS models · PanoVOS validation | J&F: XMem 48.6 (static only) -> 66.1 (with YouTube-VOS) | Improved |
| use SAM-based variants (PerSAM, SAM-PT) for zero-shot panoramic VOS | SAM · PanoVOS validation | J&F: PerSAM 19.1, SAM-PT 47.5 vs Ours-Large 77.9 | Hurt |
| re-train baselines on PanoVOS train versus using planar-trained weights | AOTS / XMem · PanoVOS validation | J&F: AOTS 66.7 -> 67.7; XMem* 63.4 -> 57.7 | Mixed |
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.
- XMem* — XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model (ECCV 2022) · 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
- Waymo Open Dataset: Panoramic Video Panoptic Segmentation (ECCV 2022 · similarity 0.89)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.88)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Geometric Exploitation for Indoor Panoramic Semantic Segmentation (NeurIPS 2024 · similarity 0.86)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.86)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (AAAI 2024 · similarity 0.86)
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.
