AI Paper Atlas

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

ECCV 2024 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add PSC attention (left-right boundary stitching) to the VOS transformer (ablation)Ours-Base · PanoVOS validationJ&F: 72.8 -> 74.0Improved
add PSC attention (ablation)Ours-Large · PanoVOS validationJ&F: 74.8 -> 77.9Improved
add PSC attention (ablation)Ours-Large · PanoVOS testJ&F: 59.5 -> 59.9No clear effect
replace cross-attention with PSC attention (ablation)Ours-Base · PanoVOS testJ&F: 54.8 -> 56.8Improved
add boundary stitching mechanism with p=2 (ablation)Ours-Large · PanoVOS validationJ&F: 73.7 -> 77.9Improved
vary stitching hyperparameter p from 2 to 5, 10 or 15 (ablation)Ours-Large · PanoVOS validationJ&F: 77.9 -> 74.2 (p=5)Hurt
deploy planar-video VOS models on panoramic videos without re-trainingoff-the-shelf VOS models · PanoVOS validationJ&F: AOTB YouTube-VOS 83.5 -> 70.5Hurt
train on larger VOS data (YouTube-VOS, BL30K)off-the-shelf VOS models · PanoVOS validationJ&F: XMem 48.6 (static only) -> 66.1 (with YouTube-VOS)Improved
use SAM-based variants (PerSAM, SAM-PT) for zero-shot panoramic VOSSAM · PanoVOS validationJ&F: PerSAM 19.1, SAM-PT 47.5 vs Ours-Large 77.9Hurt
re-train baselines on PanoVOS train versus using planar-trained weightsAOTS / XMem · PanoVOS validationJ&F: AOTS 66.7 -> 67.7; XMem* 63.4 -> 57.7Mixed

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy