Papers › Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation

Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation

1 Jul 2024IEEE Robotics and Automation Letters (RA-L) 2024 7archive 2025-07-28

Kim Ji-Yeon, Oh Hyun-Bin, Kwon Byung-Ki, Dahun Kim, Yongjin Kwon, Tae-Hyun Oh

We present Uni-DVPS, a unified model for Depth-aware Video Panoptic Segmentation (DVPS) that jointly tackles distinct vision tasks, i.e., video panoptic segmentation, monocular depth estimation, and object tracking. In contrast to the prior works that adopt diverged decoder networks tailored for each task, we propose an architecture with a unified Transformer decoder network. We design a single Transformer decoder network for multi-task learning to increase shared operations to facilitate the synergies between tasks and exhibit high efficiency. We also observe that our unified query learns instance-aware representation guided by multi-task supervision, which encourages query-based tracking and obviates the need for training extra tracking module. We validate our architectural design choices with experiments on Cityscapes-DVPS and SemKITTI-DVPS datasets. The performances of all tasks are jointly improved, and we achieve state-of-the-art results on DVPQ metric for both datasets.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous DrivingDecoderDepth EstimationDepth-aware Video Panoptic SegmentationMonocular Depth EstimationMulti-Task LearningObject TrackingPanoptic SegmentationScene UnderstandingVideo Panoptic SegmentationVideo Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections