3rd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation
This is an incremental improvement for video understanding tasks in computer vision.
The paper tackled video panoptic segmentation by enhancing the DVIS++ baseline with a query-wise ensemble and other techniques, achieving a VPQ score of 57.01 on the VIPSeg test set and placing 3rd in a challenge.
Video panoptic segmentation is an advanced task that extends panoptic segmentation by applying its concept to video sequences. In the hope of addressing the challenge of video panoptic segmentation in diverse conditions, We utilize DVIS++ as our baseline model and enhance it by introducing a comprehensive approach centered on the query-wise ensemble, supplemented by additional techniques. Our proposed approach achieved a VPQ score of 57.01 on the VIPSeg test set, and ranked 3rd in the VPS track of the 3rd Pixel-level Video Understanding in the Wild Challenge.