# MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector

Source: [MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector](<https://www.sota2.com/research/paper/68fa75e61e209131cea6a868>)

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

Data updated: 2025-10-27T06:43:58.474Z

Authors: Pan Liao, Feng Yang, Di Wu, Wenhui Zhao, Jinwen Yu

Published: 2024-05-24T03:22:55.000Z

## Abstract

Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52$\\%$ improvement in the $AP\_{3D}$ metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35$\\%$ increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.

## 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/2405.15176>)

[PDF](<https://arxiv.org/pdf/2405.15176.pdf>)
