# Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

arXiv: https://arxiv.org/abs/2310.15670 · HTML: https://mlsanity.com/paper/2310.15670/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 63 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [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)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [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)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [FUTR3D: A Unified Sensor Fusion Framework for 3D Detection](https://mlsanity.com/paper/2203.10642/) (2022)

## Built on by (most cited first, 13 of 13)

- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023)
- [Fully Sparse 3D Occupancy Prediction](https://mlsanity.com/paper/2312.17118/) (2023)
- [Embodied Understanding of Driving Scenarios](https://mlsanity.com/paper/2403.04593/) (2024)
- [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](https://mlsanity.com/paper/2312.01696/) (2023)
- [Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future](https://mlsanity.com/paper/2312.03408/) (2023)
- [SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2508.16408/) (2025)
- [LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection](https://mlsanity.com/paper/2407.10164/) (2024)
- [TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation](https://mlsanity.com/paper/2412.20911/) (2024)
- [GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models](https://mlsanity.com/paper/2501.12956/) (2025)
- [RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion](https://mlsanity.com/paper/2509.17712/) (2025)
- [NeRF-DetS: Enhanced Adaptive Spatial-wise Sampling and View-wise Fusion Strategies for NeRF-based Indoor Multi-view 3D Object Detection](https://mlsanity.com/paper/2404.13921/) (2024)
- [LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation](https://mlsanity.com/paper/2512.20217/) (2025)
- [DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2506.10242/) (2025)

## Abstract (arXiv)

Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain gap between LiDAR and camera features, coupled with the inherent incompatibility in temporal fusion, significantly hinders the effectiveness of distillation-based enhancements for apprentices. Motivated by the success of uni-modal distillation, an apprentice-friendly expert model would predominantly rely on camera features, while still achieving comparable performance to multi-modal models. To this end, we introduce VCD, a framework to improve the camera-only apprentice model, including an apprentice-friendly multi-modal expert and temporal-fusion-friendly distillation supervision. The multi-modal expert VCD-E adopts an identical structure as that of the camera-only apprentice in order to alleviate the feature disparity, and leverages LiDAR input as a depth prior to reconstruct the 3D scene, achieving the performance on par with other heterogeneous multi-modal experts. Additionally, a fine-grained trajectory-based distillation module is introduced with the purpose of individually rectifying the motion misalignment for each object in the scene. With those improvements, our camera-only apprentice VCD-A sets new state-of-the-art on nuScenes with a score of 63.1% NDS.