DepthMamba with Adaptive Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Zelin, Wang, Zhichen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929651121651712
author Meng, Zelin
Wang, Zhichen
author_facet Meng, Zelin
Wang, Zhichen
contents Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous driving. In this work, we propose a new robustness benchmark to evaluate the depth estimation system under various noisy pose settings. Surprisingly, we find current multi-view depth estimation methods or single-view and multi-view fusion methods will fail when given noisy pose settings. To tackle this challenge, we propose a two-branch network architecture which fuses the depth estimation results of single-view and multi-view branch. In specific, we introduced mamba to serve as feature extraction backbone and propose an attention-based fusion methods which adaptively select the most robust estimation results between the two branches. Thus, the proposed method can perform well on some challenging scenes including dynamic objects, texture-less regions, etc. Ablation studies prove the effectiveness of the backbone and fusion method, while evaluation experiments on challenging benchmarks (KITTI and DDAD) show that the proposed method achieves a competitive performance compared to the state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DepthMamba with Adaptive Fusion
Meng, Zelin
Wang, Zhichen
Computer Vision and Pattern Recognition
Artificial Intelligence
Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous driving. In this work, we propose a new robustness benchmark to evaluate the depth estimation system under various noisy pose settings. Surprisingly, we find current multi-view depth estimation methods or single-view and multi-view fusion methods will fail when given noisy pose settings. To tackle this challenge, we propose a two-branch network architecture which fuses the depth estimation results of single-view and multi-view branch. In specific, we introduced mamba to serve as feature extraction backbone and propose an attention-based fusion methods which adaptively select the most robust estimation results between the two branches. Thus, the proposed method can perform well on some challenging scenes including dynamic objects, texture-less regions, etc. Ablation studies prove the effectiveness of the backbone and fusion method, while evaluation experiments on challenging benchmarks (KITTI and DDAD) show that the proposed method achieves a competitive performance compared to the state-of-the-art methods.
title DepthMamba with Adaptive Fusion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.19964