# DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

arXiv: https://arxiv.org/abs/2004.01170 · HTML: https://mlsanity.com/paper/2004.01170/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 27 of 27)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Object DGCNN: 3D Object Detection using Dynamic Graphs](https://mlsanity.com/paper/2110.06923/) (2021)
- [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://mlsanity.com/paper/2112.02205/) (2021)
- [Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving](https://mlsanity.com/paper/2101.06784/) (2021)
- [Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph](https://mlsanity.com/paper/2208.03624/) (2022)
- [FWD: Real-time Novel View Synthesis with Forward Warping and Depth](https://mlsanity.com/paper/2206.08355/) (2022)
- [Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving](https://mlsanity.com/paper/2309.14491/) (2023)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation](https://mlsanity.com/paper/2207.02466/) (2022)
- [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://mlsanity.com/paper/2101.06860/) (2021)
- [Revisiting 3D Object Detection From an Egocentric Perspective](https://mlsanity.com/paper/2112.07787/) (2021)
- [From SLAM to Situational Awareness: Challenges and Survey](https://mlsanity.com/paper/2110.00273/) (2021)
- [HyperDet3D: Learning a Scene-conditioned 3D Object Detector](https://mlsanity.com/paper/2204.05599/) (2022)
- [im2nerf: Image to Neural Radiance Field in the Wild](https://mlsanity.com/paper/2209.04061/) (2022)
- [Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes](https://mlsanity.com/paper/2208.08621/) (2022)
- [A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding](https://mlsanity.com/paper/2209.05222/) (2022)
- [Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar](https://mlsanity.com/paper/2308.05478/) (2023)
- [Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild](https://mlsanity.com/paper/2111.12728/) (2021)
- [Weak-to-Strong 3D Object Detection with X-Ray Distillation](https://mlsanity.com/paper/2404.00679/) (2024)
- [GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System](https://mlsanity.com/paper/2404.04118/) (2024)
- [Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior](https://mlsanity.com/paper/2107.10898/) (2021)
- [3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning](https://mlsanity.com/paper/2208.14796/) (2022)
- [Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion](https://mlsanity.com/paper/2303.01804/) (2023)

## Abstract (arXiv)

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes. The core novelty of our method is a fast, single-pass architecture that both detects objects in 3D and estimates their shapes. 3D bounding box parameters are estimated in one pass for every point, aggregated through graph convolutions, and fed into a branch of the network that predicts latent codes representing the shape of each detected object. The latent shape space and shape decoder are learned on a synthetic dataset and then used as supervision for the end-to-end training of the 3D object detection pipeline. Thus our model is able to extract shapes without access to ground-truth shape information in the target dataset. During experiments, we find that our proposed method achieves state-of-the-art results by ~5% on object detection in ScanNet scenes, and it gets top results by 3.4% in the Waymo Open Dataset, while reproducing the shapes of detected cars.