# MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models

Source: [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](<https://www.sota2.com/research/paper/68fa77831e209131cea73b78>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:20:40.032Z

Authors: Johannes Meier, Louis Inchingolo, Oussema Dhaouadi, Yan Xia, Jacques Kaiser, Daniel Cremers

Published: 2025-03-17T21:59:41.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.13743>)

[PDF](<https://arxiv.org/pdf/2503.13743.pdf>)
