# Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

arXiv: https://arxiv.org/abs/1911.11288 · HTML: https://mlsanity.com/paper/1911.11288/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 30 of 74)

- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator](https://mlsanity.com/paper/2102.12145/) (2021)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (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)
- [ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization](https://mlsanity.com/paper/2207.13691/) (2022)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [AutoRF: Learning 3D Object Radiance Fields from Single View Observations](https://mlsanity.com/paper/2204.03593/) (2022)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Waymo Open Dataset: Panoramic Video Panoptic Segmentation](https://mlsanity.com/paper/2206.07704/) (2022)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Auto4D: Learning to Label 4D Objects from Sequential Point Clouds](https://mlsanity.com/paper/2101.06586/) (2021)
- [Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2203.10339/) (2022)
- [DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation](https://mlsanity.com/paper/2207.02805/) (2022)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [Lidar Point Cloud Guided Monocular 3D Object Detection](https://mlsanity.com/paper/2104.09035/) (2021)
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://mlsanity.com/paper/2205.06267/) (2022)
- [Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors](https://mlsanity.com/paper/2303.14505/) (2023)
- [Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection](https://mlsanity.com/paper/2304.12315/) (2023)
- [Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping](https://mlsanity.com/paper/2306.01405/) (2023)
- [Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching](https://mlsanity.com/paper/2108.03746/) (2021)
- [TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2212.12902/) (2022)
- [DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM](https://mlsanity.com/paper/2401.01545/) (2024)
- [Latent Partition Implicit with Surface Codes for 3D Representation](https://mlsanity.com/paper/2207.08631/) (2022)
- [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://mlsanity.com/paper/2101.06860/) (2021)
- [FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects](https://mlsanity.com/paper/2310.12974/) (2023)
- [WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2203.08332/) (2022)
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://mlsanity.com/paper/2303.08686/) (2023)
- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [PRIF: Primary Ray-based Implicit Function](https://mlsanity.com/paper/2208.06143/) (2022)

## Abstract (arXiv)

We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To address this challenging problem, we apply a novel differentiable shape renderer to signed distance fields (SDF), leveraged together with normalized object coordinate spaces (NOCS). Initially trained on synthetic data to predict shape and coordinates, our method uses these predictions for projective and geometric alignment over real samples. Moreover, we also propose a curriculum learning strategy, iteratively retraining on samples of increasing difficulty in subsequent self-improving annotation rounds. Our experiments on the KITTI3D dataset show that we can recover a substantial amount of accurate cuboids, and that these autolabels can be used to train 3D vehicle detectors with state-of-the-art results.