References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: Joint Depth Prediction and Semantic Segmentation with Multi-View SAM
(Submitted on 31 Oct 2023)
Abstract: Multi-task approaches to joint depth and segmentation prediction are well-studied for monocular images. Yet, predictions from a single-view are inherently limited, while multiple views are available in many robotics applications. On the other end of the spectrum, video-based and full 3D methods require numerous frames to perform reconstruction and segmentation. With this work we propose a Multi-View Stereo (MVS) technique for depth prediction that benefits from rich semantic features of the Segment Anything Model (SAM). This enhanced depth prediction, in turn, serves as a prompt to our Transformer-based semantic segmentation decoder. We report the mutual benefit that both tasks enjoy in our quantitative and qualitative studies on the ScanNet dataset. Our approach consistently outperforms single-task MVS and segmentation models, along with multi-task monocular methods.
Submission history
From: Mykhailo Shvets [view email][v1] Tue, 31 Oct 2023 20:15:40 GMT (10240kb,D)
Link back to: arXiv, form interface, contact.