RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo

TL;DR

RobIA introduces a robust, instance-aware framework for continual test-time adaptation in stereo depth estimation, effectively handling domain shifts with dynamic routing and dense pseudo-supervision.

Contribution

It proposes RobIA, combining a dynamic routing module and a dense pseudo-supervision teacher to improve continual adaptation under domain shifts.

Findings

Achieves superior adaptation performance across dynamic domains.

Maintains computational efficiency during adaptation.

Enhances generalization under challenging domain shifts.

Abstract

Stereo Depth Estimation in real-world environments poses significant challenges due to dynamic domain shifts, sparse or unreliable supervision, and the high cost of acquiring dense ground-truth labels. While recent Test-Time Adaptation (TTA) methods offer promising solutions, most rely on static target domain assumptions and input-invariant adaptation strategies, limiting their effectiveness under continual shifts. In this paper, we propose RobIA, a novel Robust, Instance-Aware framework for Continual Test-Time Adaptation (CTTA) in stereo depth estimation. RobIA integrates two key components: (1) Attend-and-Excite Mixture-of-Experts (AttEx-MoE), a parameter-efficient module that dynamically routes input to frozen experts via lightweight self-attention mechanism tailored to epipolar geometry, and (2) Robust AdaptBN Teacher, a PEFT-based teacher model that provides dense pseudo-supervision by complementing sparse handcrafted labels. This strategy enables input-specific flexibility, broad supervision coverage, improving generalization under domain shift. Extensive experiments demonstrate that RobIA achieves superior adaptation performance across dynamic target domains while maintaining computational efficiency.