Task-Aware Monocular Depth Estimation for 3D Object Detection
Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.
Code (1)
Tasks
3D Object Detection3D Object RecognitionDepth EstimationDepth PredictionMonocular Depth EstimationObjectobject-detectionObject DetectionObject RecognitionSimilar Papers 제목 키워드 기반
MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts
Monocular 3D object detection reveals an economical but challenging task in autonomous driving. Recently center-based monocular methods have developed rapidly with a great trade-off between speed and accuracy, where they…
3D Object DetectionAutonomous DrivingDepth EstimationMonocular 3D Object Detection+3Learning Monocular Depth in Dynamic Environment via Context-aware Temporal Attention
The monocular depth estimation task has recently revealed encouraging prospects, especially for the autonomous driving task. To tackle the ill-posed problem of 3D geometric reasoning from 2D monocular images, multi-frame…
Autonomous DrivingDepth EstimationMonocular Depth EstimationPose EstimationDepth-Aware Rover: A Study of Edge AI and Monocular Vision for Real-World Implementation
This study analyses simulated and real-world implementations of depth-aware rover navigation, highlighting the transition from stereo vision to monocular depth estimation using edge AI. A Unity-based lunar terrain simula…
Monocular Depth EstimationReal-Time Object DetectionLearning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to the unsatisfactory performance in depth es…
3D Object DetectionAutonomous DrivingDepth EstimationMonocular 3D Object Detection+4CutDepth:Edge-aware Data Augmentation in Depth Estimation
It is difficult to collect data on a large scale in a monocular depth estimation because the task requires the simultaneous acquisition of RGB images and depths. Data augmentation is thus important to this task. However,…
Data AugmentationDepth EstimationMonocular Depth Estimation