ELFNet: Evidential Local-global Fusion for Stereo Matching

TL;DR

ELFNet introduces an evidential fusion framework for stereo matching that estimates uncertainty and effectively leverages multi-scale and multi-view information, achieving state-of-the-art accuracy and generalization.

Contribution

The paper presents a novel evidential fusion framework for stereo matching that incorporates uncertainty estimation and multi-view knowledge integration.

Findings

Achieves state-of-the-art accuracy in stereo matching.

Demonstrates improved cross-domain generalization.

Effectively exploits multi-view information.

Abstract

Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation. Additionally, effectively leveraging multi-scale and multi-view knowledge of stereo pairs remains unexplored. In this paper, we introduce the \textbf{E}vidential \textbf{L}ocal-global \textbf{F}usion (ELF) framework for stereo matching, which endows both uncertainty estimation and confidence-aware fusion with trustworthy heads. Instead of predicting the disparity map alone, our model estimates an evidential-based disparity considering both aleatoric and epistemic uncertainties. With the normal inverse-Gamma distribution as a bridge, the proposed framework realizes intra evidential fusion of multi-level predictions and inter evidential fusion between cost-volume-based and transformer-based stereo matching. Extensive experimental results show that the proposed framework exploits multi-view information effectively and achieves state-of-the-art overall performance both on accuracy and cross-domain generalization. The codes are available at https://github.com/jimmy19991222/ELFNet.