Sketchy Bounding-box Supervision for 3D Instance Segmentation
Qian Deng, Le Hui, Jin Xie, Jian Yang

TL;DR
This paper introduces Sketchy-3DIS, a weakly supervised 3D instance segmentation method that effectively learns from imprecise bounding boxes by jointly training a pseudo labeler and segmentator, achieving state-of-the-art results.
Contribution
The paper proposes a novel framework that improves 3D instance segmentation using sketchy bounding boxes by jointly learning pseudo labels and segmentation, outperforming existing methods.
Findings
Achieves state-of-the-art results on ScanNetV2 and S3DIS benchmarks.
Outperforms several fully supervised methods with sketchy bounding boxes.
Effectively learns from imprecise bounding box annotations.
Abstract
Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation. While this approach alleviates the need for extensive point-level annotations, obtaining accurate bounding boxes in practical applications remains challenging. To this end, we explore the inaccurate bounding box, named sketchy bounding box, which is imitated through perturbing ground truth bounding box by adding scaling, translation, and rotation. In this paper, we propose Sketchy-3DIS, a novel weakly 3D instance segmentation framework, which jointly learns pseudo labeler and segmentator to improve the performance under the sketchy bounding-box supervisions. Specifically, we first propose an adaptive box-to-point pseudo labeler that adaptively learns to assign points located in the overlapped parts between two sketchy bounding boxes to the correct instance, resulting in compact and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · 3D Shape Modeling and Analysis · Robotics and Sensor-Based Localization
MethodsSoftmax · Attention Is All You Need
