In recent years, deep neural networks have shown remarkable progress in dense disparity estimation from dynamic scenes in monocular structured light systems. However, their performance significantly drops when applied in unseen environments. To address this issue, self-supervised online adaptation has been proposed as a solution to bridge this performance gap. Unlike traditional fine-tuning processes, online adaptation performs test-time optimization to adapt networks to new domains. Therefore, achieving fast convergence during the adaptation process is critical for attaining satisfactory accuracy. In this paper, we propose an unsupervised loss function based on long sequential inputs. It ensures better gradient directions and faster convergence. Our loss function is designed using a multi-frame pattern flow, which comprises a set of sparse trajectories of the projected pattern along the sequence. We estimate the sparse pseudo ground truth with a confidence mask using a filter-based method, which guides the online adaptation process. Our proposed framework significantly improves the online adaptation speed and achieves superior performance on unseen data.

翻译：近年来，深度神经网络在单目结构光系统中动态场景的密集视差估计方面取得了显著进展。然而，当应用于未见过的环境时，其性能会大幅下降。为解决该问题，自监督在线自适应被提出弥合这一性能差距。与传统微调流程不同，在线自适应在测试阶段进行优化，使网络适应新领域。因此，在自适应过程中实现快速收敛对于获得满意的精度至关重要。本文提出一种基于长序列输入的无监督损失函数，可确保更优的梯度方向和更快的收敛速度。该损失函数利用多帧模式光流进行设计，该光流包含投影模式沿序列的稀疏轨迹集。我们通过基于滤波的方法估计带有置信度掩码的稀疏伪真实值，从而引导在线自适应过程。本文提出的框架显著提升了在线自适应速度，并在未见数据上取得了优越性能。