# End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection

arXiv: https://arxiv.org/abs/2004.03080 · HTML: https://mlsanity.com/paper/2004.03080/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 30 of 80)

- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2108.11127/) (2021)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions](https://mlsanity.com/paper/2208.01166/) (2022)
- [Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection](https://mlsanity.com/paper/2205.09373/) (2022)
- [NeRF-RPN: A general framework for object detection in NeRFs](https://mlsanity.com/paper/2211.11646/) (2022)
- [CAPE: Camera View Position Embedding for Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.10209/) (2023)
- [YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection](https://mlsanity.com/paper/2103.09422/) (2021)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://mlsanity.com/paper/2206.07705/) (2022)
- [IPS300+: a Challenging Multimodal Dataset for Intersection Perception System](https://mlsanity.com/paper/2106.02781/) (2021)
- [Homography Loss for Monocular 3D Object Detection](https://mlsanity.com/paper/2204.00754/) (2022)
- [OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01142/) (2022)
- [Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection](https://mlsanity.com/paper/2103.14198/) (2021)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching](https://mlsanity.com/paper/2306.15612/) (2023)
- [Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception](https://mlsanity.com/paper/2301.07870/) (2023)
- [Viewpoint Equivariance for Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.14548/) (2023)

## Abstract (arXiv)

Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. However, so far these two networks have to be trained separately. In this paper, we introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end. The resulting framework is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks -- yielding the highest entry on the KITTI image-based 3D object detection leaderboard at the time of submission. Our code will be made available at https://github.com/mileyan/pseudo-LiDAR_e2e.