Congrats to TRAIL Lab grad student Anas Mahmoud and Robotics Institute faculty member Steve Waslander for winning the Best Computer Vision Paper at this year’s Conference on Robots and Vision (CRV2021).
Their paper, Sequential Fusion via Bounding Box and Motion PointPainting for 3D Objection Detection, proposes class-aware and class-agnostic point painting methods which employ predicted bounding boxes from image-based 2D object detectors to extract coarse image semantics instead of full scene semantic segmentation.