TarViS: A Unified Approach for Target-based Video Segmentation

Understand

The general domain of video segmentation is currently fragmented into different tasks spanning multiple benchmarks.

• Despite rapid progress in the state-of-the-art, current methods are overwhelmingly task-specific and cannot conceptually generalize to other tasks.
• Inspired by recent approaches with multi-task capability, we propose TarViS: a novel, unified network architecture that can be applied to any task that requires segmenting a set of arbitrarily defined 'targets' in video.
• Our approach is flexible with respect to how tasks define these targets, since it models the latter as abstract 'queries' which are then used to predict pixel-precise target masks.