# Joint Depth Prediction and Semantic Segmentation with Multi-View SAM

Source: [Joint Depth Prediction and Semantic Segmentation with Multi-View SAM](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0fd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:57:41.618Z

Authors: Mykhailo Shvets, Dongxu Zhao, Marc Niethammer, Roni Sengupta, Alexander C. Berg

Published: 2023-10-31T20:15:40.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.00134>)

[PDF](<https://arxiv.org/pdf/2311.00134.pdf>)