# GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection

Source: [GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection](<https://www.sota2.com/research/paper/68fa6fed1e209131cea48348>)

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

Data updated: 2025-10-28T13:56:59.786Z

Authors: Weixin Mao, Jinrong Yang, Zheng Ge, Lin Song, Hongyu Zhou, Tiezheng Mao, Zeming Li, Osamu Yoshie

Published: 2023-06-30T07:52:23.000Z

## Abstract

Depth perception is a crucial component of monoc-ular 3D detection tasks that typically involve ill-posed problems. In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effective mining strategy for improving depth perception in 3D object detection. Concretely, we introduce a plain metric to evaluate the quality of depth predictions, which chooses the mined sample for the model. Moreover, we propose a Gradient-aware and Model-perceive Mining strategy (GMM) for depth learning, which exploits the predicted depth quality for better depth learning through easy mining. GMM is a general strategy that can be readily applied to several state-of-the-art monocular 3D detectors, improving the accuracy of depth prediction. Extensive experiments on the nuScenes dataset demonstrate that the proposed methods significantly improve the performance of 3D object detection while outperforming other state-of-the-art sample mining techniques by a considerable margin. On the nuScenes benchmark, GMM achieved the state-of-the-art (42.1% mAP and 47.3% NDS) performance in monocular object detection.

## 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/2306.17450>)

[PDF](<https://arxiv.org/pdf/2306.17450.pdf>)
