Geometry-Aware Instance Segmentation with Disparity Maps
This addresses instance segmentation in autonomous driving scenarios by improving accuracy through sensor fusion, though it appears incremental as it builds on existing stereo and segmentation approaches.
The paper tackles outdoor instance segmentation by fusing stereo camera data with color images, using geometric information from disparity maps to separate overlapping objects and reduce false positives. The method achieves state-of-the-art performance on a new high-quality driving stereo dataset.
Most previous works of outdoor instance segmentation for images only use color information. We explore a novel direction of sensor fusion to exploit stereo cameras. Geometric information from disparities helps separate overlapping objects of the same or different classes. Moreover, geometric information penalizes region proposals with unlikely 3D shapes thus suppressing false positive detections. Mask regression is based on 2D, 2.5D, and 3D ROI using the pseudo-lidar and image-based representations. These mask predictions are fused by a mask scoring process. However, public datasets only adopt stereo systems with shorter baseline and focal legnth, which limit measuring ranges of stereo cameras. We collect and utilize High-Quality Driving Stereo (HQDS) dataset, using much longer baseline and focal length with higher resolution. Our performance attains state of the art. Please refer to our project page. The full paper is available here.