Abstract
The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer representation. This is implemented using a variant of the transformer architecture that ingests optical flow, where each query vector specifies an object and its layer for the entire video. The model can effectively discover multiple moving objects and handle mutual occlusions; Second, we introduce a scalable pipeline for generating synthetic training data with multiple objects, significantly reducing the requirements for labour-intensive annotations, and supporting Sim2Real generalisation; Third, we show that the model is able to learn object permanence and temporal shape consistency, and is able to predict amodal segmentation masks; Fourth, we evaluate the model on standard video segmentation benchmarks, DAVIS, MoCA, SegTrack, FBMS-59, and achieve state-of-the-art unsupervised segmentation performance, even outperforming several supervised approaches. With test-time adaptation, we observe further performance boosts.
Abstract (translated)
URL
https://arxiv.org/abs/2207.02206
