# X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection

arXiv: https://arxiv.org/abs/2303.02203 · HTML: https://mlsanity.com/paper/2303.02203/

## Key facts

- Cited by 28 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 57 of its 65 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## 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 57)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)

## Built on by (most cited first, 28 of 28)

- [Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception](https://mlsanity.com/paper/2403.07746/) (2024)
- [RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features](https://mlsanity.com/paper/2403.05061/) (2024)
- [CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation](https://mlsanity.com/paper/2403.19104/) (2024)
- [LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Camera](https://mlsanity.com/paper/2407.16197/) (2024)
- [SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects](https://mlsanity.com/paper/2403.20318/) (2024)
- [Multi-modal Knowledge Distillation-based Human Trajectory Forecasting](https://mlsanity.com/paper/2503.22201/) (2025)
- [SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection](https://mlsanity.com/paper/2308.13794/) (2023)
- [LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection](https://mlsanity.com/paper/2407.10164/) (2024)
- [Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey](https://mlsanity.com/paper/2410.19872/) (2024)
- [SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation](https://mlsanity.com/paper/2506.17290/) (2025)
- [Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception](https://mlsanity.com/paper/2405.07201/) (2024)
- [SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2411.19860/) (2024)
- [CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective](https://mlsanity.com/paper/2404.14109/) (2024)
- [ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles](https://mlsanity.com/paper/2309.03734/) (2023)
- [TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation](https://mlsanity.com/paper/2412.20911/) (2024)
- [LEROjD: Lidar Extended Radar-Only Object Detection](https://mlsanity.com/paper/2409.05564/) (2024)
- [CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation](https://mlsanity.com/paper/2503.09878/) (2025)
- [RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion](https://mlsanity.com/paper/2509.17712/) (2025)
- [DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning](https://mlsanity.com/paper/2404.06352/) (2024)
- [Boosting Instance Awareness via Cross-View Correlation with 4D Radar and Camera for 3D Object Detection](https://mlsanity.com/paper/2602.20632/) (2026)
- [X-Align++: cross-modal cross-view alignment for Bird's-eye-view segmentation](https://mlsanity.com/paper/2306.03810/) (2023)
- [Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy](https://mlsanity.com/paper/2507.21358/) (2025)
- [TinyBEV: Cross Modal Knowledge Distillation for Efficient Multi Task Bird's Eye View Perception and Planning](https://mlsanity.com/paper/2509.18372/) (2025)
- [Dataset Safety in Autonomous Driving: Requirements, Risks, and Assurance](https://mlsanity.com/paper/2511.08439/) (2025)
- [IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion](https://mlsanity.com/paper/2512.15581/) (2025)
- [LiDAR-Anchored Collaborative Distillation for Robust 2D Representations](https://mlsanity.com/paper/2602.12524/) (2026)
- [LiAuto-GeoX: Efficient Grounded Driving Transformer](https://mlsanity.com/paper/2606.05774/) (2026)
- [Close Shortcut Wins Long: Seeking Diverse and Stable Generators for Data-Free Knowledge Distillation](https://mlsanity.com/paper/2608.22003/) (2026)

## Abstract (arXiv)

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of features from perspective view (PV) to a 3D world representation which is ambiguous due to missing depth information. This paper introduces X3KD, a comprehensive knowledge distillation framework across different modalities, tasks, and stages for multi-camera 3DOD. Specifically, we propose cross-task distillation from an instance segmentation teacher (X-IS) in the PV feature extraction stage providing supervision without ambiguous error backpropagation through the view transformation. After the transformation, we apply cross-modal feature distillation (X-FD) and adversarial training (X-AT) to improve the 3D world representation of multi-camera features through the information contained in a LiDAR-based 3DOD teacher. Finally, we also employ this teacher for cross-modal output distillation (X-OD), providing dense supervision at the prediction stage. We perform extensive ablations of knowledge distillation at different stages of multi-camera 3DOD. Our final X3KD model outperforms previous state-of-the-art approaches on the nuScenes and Waymo datasets and generalizes to RADAR-based 3DOD. Qualitative results video at https://youtu.be/1do9DPFmr38.