Back2Color: Domain-Adaptive Synthetic-to-Real Monocular Depth Estimation for Dynamic Traffic Scenes

TL;DR

Back2Color introduces a domain-adaptive, uncertainty-aware framework for monocular depth estimation in traffic scenes, effectively bridging synthetic-to-real gaps and handling dynamic objects to improve accuracy and robustness.

Contribution

The paper proposes a novel bidirectional depth-to-color transformation and an auto-learning uncertainty fusion module to enhance unsupervised monocular depth estimation in dynamic traffic environments.

Findings

Outperforms existing methods on KITTI and Cityscapes benchmarks.

Effectively reduces domain gap between synthetic and real data.

Improves robustness in dynamic scenes with moving objects.

Abstract

Accurate monocular depth estimation is a fundamental component of vision-based perception systems in intelligent transportation applications. Despite recent progress, unsupervised monocular approaches still suffer from significant performance degradation in real-world traffic scenes due to synthetic-to-real domain gaps and the presence of dynamic, non-rigid objects such as vehicles and pedestrians. In this paper, we propose Back2Color, a robust unsupervised monocular depth estimation framework that addresses these challenges through domain adaptation and uncertainty-aware fusion. Specifically, Back2Color proposes a bidirectional depth-to-color transformation strategy that learns appearance mappings from real-world driving data and applies them to synthetic depth maps, thereby constructing training samples with realistic color appearance and paired synthetic depth. In this way, the proposed approach effectively reduces the domain gap between simulated and real traffic scenes, enabling the depth prediction network to learn more stable and generalizable priors. To further improve robustness under dynamic environments, we propose an auto-learning uncertainty temporal-spatial fusion (Auto-UTSF) module, which adaptively fuses complementary temporal and spatial cues by estimating pixel-wise uncertainty, enabling reliable depth prediction in the presence of moving objects and occlusions. Extensive experiments on challenging urban driving benchmarks, including KITTI and Cityscapes, demonstrate that the proposed method consistently outperforms existing unsupervised monocular depth estimation approaches, particularly in dynamic traffic scenarios, while maintaining high computational efficiency.