# Task-Aware Monocular Depth Estimation for 3D Object Detection

arXiv: https://arxiv.org/abs/1909.07701 · HTML: https://mlsanity.com/paper/1909.07701/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 22 of 22)

- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2108.11127/) (2021)
- [MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation](https://mlsanity.com/paper/2103.12605/) (2021)
- [MonoDistill: Learning Spatial Features for Monocular 3D Object Detection](https://mlsanity.com/paper/2201.10830/) (2022)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01142/) (2022)
- [ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection](https://mlsanity.com/paper/2308.09098/) (2023)
- [NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization](https://mlsanity.com/paper/2305.17763/) (2023)
- [Generic Perceptual Loss for Modeling Structured Output Dependencies](https://mlsanity.com/paper/2103.10571/) (2021)
- [Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking](https://mlsanity.com/paper/2206.03666/) (2022)
- [Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision](https://mlsanity.com/paper/2210.16574/) (2022)
- [GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models](https://mlsanity.com/paper/2406.12671/) (2024)
- [Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection](https://mlsanity.com/paper/2103.03977/) (2021)
- [Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection](https://mlsanity.com/paper/2310.05447/) (2023)
- [Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection](https://mlsanity.com/paper/2411.02747/) (2024)
- [Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection](https://mlsanity.com/paper/2603.07464/) (2026)
- [Monocular Depth Estimation from a Single Image: Progress and Opportunities](https://mlsanity.com/paper/2609.01172/) (2026)

## Abstract (arXiv)

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.