Year: 2025
Type: preprint
Abstract: We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo labels for self-supervision. Inspired by our observation that accurate depth estimation is critical to mitigating domain shifts, MonoCT introduces a novel Generalized Depth Enhancement (GDE) module with an ensemble concept to improve depth estimation accuracy. Moreover, we introduce a novel Pseudo Label Scoring (PLS) module by exploring inner-model consistency measurement and a Diversity Maximization (DM) strategy to further generate high-quality pseudo labels for self-training. Extensive experiments on six benchmarks show that MonoCT outperforms existing SOTA domain adaptation methods by large margins (~21% minimum for AP Mod.) and generalizes well to car, traffic camera and drone views.
Source: arXiv (Cornell University)
Authors: Meier, Johannes, Inchingolo, Louis, Dhaouadi, Oussema, Xia, Yan, Kaiser, Jacques, Cremers, Daniel
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979312488
Cites:
Cited by:
Related to: