# RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation

arXiv: https://arxiv.org/abs/2312.11829 · HTML: https://mlsanity.com/paper/2312.11829/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 30 of 34)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [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)
- [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)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021)
- [Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation](https://mlsanity.com/paper/2008.01550/) (2020)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo](https://mlsanity.com/paper/2209.10248/) (2022)

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

- [OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2403.01644/) (2024)
- [Vision-based 3D occupancy prediction in autonomous driving: a review and outlook](https://mlsanity.com/paper/2405.02595/) (2024)
- [Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities](https://mlsanity.com/paper/2401.08045/) (2024)
- [Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding](https://mlsanity.com/paper/2408.13024/) (2024)
- [GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision](https://mlsanity.com/paper/2405.10591/) (2024)
- [An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training](https://mlsanity.com/paper/2412.13772/) (2024)
- [ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder](https://mlsanity.com/paper/2412.08774/) (2024)
- [DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction](https://mlsanity.com/paper/2409.19972/) (2024)
- [VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2411.14716/) (2024)
- [GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention](https://mlsanity.com/paper/2505.10685/) (2025)
- [Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving](https://mlsanity.com/paper/2403.08504/) (2024)
- [3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation](https://mlsanity.com/paper/2503.15185/) (2025)
- [EFFOcc: Learning Efficient Occupancy Networks from Minimal Labels for Autonomous Driving](https://mlsanity.com/paper/2406.07042/) (2024)
- [Inverse++: Vision-Centric 3D Semantic Occupancy Prediction Assisted with 3D Object Detection](https://mlsanity.com/paper/2504.04732/) (2025)
- [SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving](https://mlsanity.com/paper/2509.16588/) (2025)
- [MetaOcc: Spatio-Temporal Fusion of Surround-View 4D Radar and Camera for 3D Occupancy Prediction with Dual Training Strategies](https://mlsanity.com/paper/2501.15384/) (2025)
- [Event-aided Semantic Scene Completion](https://mlsanity.com/paper/2502.02334/) (2025)
- [Out-of-Distribution Semantic Occupancy Prediction](https://mlsanity.com/paper/2506.21185/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction](https://mlsanity.com/paper/2603.22852/) (2026)
- [BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network](https://mlsanity.com/paper/2405.17037/) (2024)
- [α-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2406.11021/) (2024)
- [D2-World: An Efficient World Model through Decoupled Dynamic Flow](https://mlsanity.com/paper/2411.17027/) (2024)
- [TFusionOcc: T-Primitive Based Object-Centric Multi-Sensor Fusion Framework for 3D Occupancy Prediction](https://mlsanity.com/paper/2602.06400/) (2026)
- [Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy](https://mlsanity.com/paper/2605.05072/) (2026)
- [3D Reconstruction and Knowledge Distillation to Improve Multi-View Image Models to Explore Spike Volume Estimation in Wheat](https://mlsanity.com/paper/2605.20940/) (2026)
- [Semantic Occupancy Prediction with Dual Range-Voxel Representation](https://mlsanity.com/paper/2606.31688/) (2026)

## Abstract (arXiv)

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate prediction due to the absence of geometric priors. In this paper, we address this issue by exploring cross-modal knowledge distillation in this task, i.e., we leverage a stronger multi-modal model to guide the visual model during training. In practice, we observe that directly applying features or logits alignment, proposed and widely used in bird's-eyeview (BEV) perception, does not yield satisfactory results. To overcome this problem, we introduce RadOcc, a Rendering assisted distillation paradigm for 3D Occupancy prediction. By employing differentiable volume rendering, we generate depth and semantic maps in perspective views and propose two novel consistency criteria between the rendered outputs of teacher and student models. Specifically, the depth consistency loss aligns the termination distributions of the rendered rays, while the semantic consistency loss mimics the intra-segment similarity guided by vision foundation models (VLMs). Experimental results on the nuScenes dataset demonstrate the effectiveness of our proposed method in improving various 3D occupancy prediction approaches, e.g., our proposed methodology enhances our baseline by 2.2% in the metric of mIoU and achieves 50% in Occ3D benchmark.