Multi-Object Discovery by Low-Dimensional Object Motion
This work addresses multi-object segmentation for computer vision applications, but it is incremental as it builds on existing motion prediction methods by incorporating scene structure constraints.
The paper tackled the problem of unsupervised multi-object segmentation by modeling pixel-wise geometry and object motion to remove ambiguity in predicting flow from a single image, achieving state-of-the-art results on synthetic and real-world datasets.
Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without the next image. On the other hand, the set of possible motions for an image can be constrained to a low-dimensional space by considering the scene structure and moving objects in it. We propose to model pixel-wise geometry and object motion to remove ambiguity in reconstructing flow from a single image. Specifically, we divide the image into coherently moving regions and use depth to construct flow bases that best explain the observed flow in each region. We achieve state-of-the-art results in unsupervised multi-object segmentation on synthetic and real-world datasets by modeling the scene structure and object motion. Our evaluation of the predicted depth maps shows reliable performance in monocular depth estimation.