# Weak-to-Strong 3D Object Detection with X-Ray Distillation arXiv: https://arxiv.org/abs/2404.00679 ยท HTML: https://mlsanity.com/paper/2404.00679/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. - Builds on 36 of its 52 references that are in the map. - First posted on arXiv 31 Mar 2024. ## Placed in - Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/) ## Builds on (most cited first, 30 of 36) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016) - [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019) - [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017) - [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019) - [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020) - [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020) - [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022) - [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023) - [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018) - [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016) - [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019) - [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019) - [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021) - [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019) - [DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets](https://mlsanity.com/paper/2301.06051/) (2023) - [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019) - [CenterFormer: Center-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2209.05588/) (2022) - [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019) - [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2012.04355/) (2020) - [UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation](https://mlsanity.com/paper/2308.07732/) (2023) - [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://mlsanity.com/paper/2112.02205/) (2021) - [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022) - [Learning general and distinctive 3D local deep descriptors for point cloud registration](https://mlsanity.com/paper/2105.10382/) (2021) - [Augmented LiDAR Simulator for Autonomous Driving](https://mlsanity.com/paper/1811.07112/) (2018) - [EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection](https://mlsanity.com/paper/2303.17895/) (2023) - [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022) - [DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes](https://mlsanity.com/paper/2004.01170/) (2020) - [Probabilistic Oriented Object Detection in Automotive Radar](https://mlsanity.com/paper/2004.05310/) (2020) - [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023) ## Built on by (most cited first, 5 of 5) - [Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds](https://mlsanity.com/paper/2505.17442/) (2025) - [Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision](https://mlsanity.com/paper/2510.07703/) (2025) - [GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2512.23147/) (2025) - [From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning](https://mlsanity.com/paper/2503.06282/) (2025) - [Weak-to-Strong Knowledge Distillation Accelerates Visual Learning](https://mlsanity.com/paper/2604.15451/) (2026) ## Abstract (arXiv) This paper addresses the critical challenges of sparsity and occlusion in LiDAR-based 3D object detection. Current methods often rely on supplementary modules or specific architectural designs, potentially limiting their applicability to new and evolving architectures. To our knowledge, we are the first to propose a versatile technique that seamlessly integrates into any existing framework for 3D Object Detection, marking the first instance of Weak-to-Strong generalization in 3D computer vision. We introduce a novel framework, X-Ray Distillation with Object-Complete Frames, suitable for both supervised and semi-supervised settings, that leverages the temporal aspect of point cloud sequences. This method extracts crucial information from both previous and subsequent LiDAR frames, creating Object-Complete frames that represent objects from multiple viewpoints, thus addressing occlusion and sparsity. Given the limitation of not being able to generate Object-Complete frames during online inference, we utilize Knowledge Distillation within a Teacher-Student framework. This technique encourages the strong Student model to emulate the behavior of the weaker Teacher, which processes simple and informative Object-Complete frames, effectively offering a comprehensive view of objects as if seen through X-ray vision. Our proposed methods surpass state-of-the-art in semi-supervised learning by 1-1.5 mAP and enhance the performance of five established supervised models by 1-2 mAP on standard autonomous driving datasets, even with default hyperparameters. Code for Object-Complete frames is available here: https://github.com/sakharok13/X-Ray-Teacher-Patching-Tools.