# Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation

arXiv: https://arxiv.org/abs/2404.11958 · HTML: https://mlsanity.com/paper/2404.11958/

## Key facts

- Cited by 43 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 54 of its 66 references that are in the map.
- First posted on arXiv 18 Apr 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 54)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [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)
- [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)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior](https://mlsanity.com/paper/2003.14052/) (2020)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Masked Generative Distillation](https://mlsanity.com/paper/2205.01529/) (2022)

## Built on by (most cited first, 30 of 43)

- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective](https://mlsanity.com/paper/2405.05173/) (2024)
- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning](https://mlsanity.com/paper/2504.16023/) (2025)
- [VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection](https://mlsanity.com/paper/2506.04623/) (2025)
- [Label-efficient Semantic Scene Completion with Scribble Annotations](https://mlsanity.com/paper/2405.15170/) (2024)
- [Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2501.07260/) (2025)
- [3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation](https://mlsanity.com/paper/2503.15185/) (2025)
- [L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model](https://mlsanity.com/paper/2503.12369/) (2025)
- [OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera](https://mlsanity.com/paper/2511.03571/) (2025)
- [Robust 3D Semantic Occupancy Prediction with Calibration-free Spatial Transformation](https://mlsanity.com/paper/2411.12177/) (2024)
- [Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion](https://mlsanity.com/paper/2507.08555/) (2025)
- [VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions](https://mlsanity.com/paper/2507.19188/) (2025)
- [ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning](https://mlsanity.com/paper/2409.18026/) (2024)
- [VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion](https://mlsanity.com/paper/2503.06219/) (2025)
- [Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion](https://mlsanity.com/paper/2411.16129/) (2024)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [Event-aided Semantic Scene Completion](https://mlsanity.com/paper/2502.02334/) (2025)
- [Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance](https://mlsanity.com/paper/2502.14520/) (2025)
- [Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction](https://mlsanity.com/paper/2503.23109/) (2025)
- [IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals](https://mlsanity.com/paper/2506.20671/) (2025)
- [SAM4D: Segment Anything in Camera and LiDAR Streams](https://mlsanity.com/paper/2506.21547/) (2025)
- [One Step Closer: Creating the Future to Boost Monocular Semantic Scene Completion](https://mlsanity.com/paper/2507.13801/) (2025)
- [CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation](https://mlsanity.com/paper/2510.13245/) (2025)
- [Enhancing 3D Semantic Scene Completion with a Refinement Module](https://mlsanity.com/paper/2512.18363/) (2025)
- [AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments](https://mlsanity.com/paper/2603.25494/) (2026)
- [Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations](https://mlsanity.com/paper/2503.06222/) (2025)
- [GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction](https://mlsanity.com/paper/2506.14825/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving](https://mlsanity.com/paper/2603.19675/) (2026)

## Abstract (arXiv)

Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately, existing methods usually formulate this task as a voxel-wise classification problem and treat each voxel equally in 3D space during training. As the hard voxels have not been paid enough attention, the performance in some challenging regions is limited. The 3D dense space typically contains a large number of empty voxels, which are easy to learn but require amounts of computation due to handling all the voxels uniformly for the existing models. Furthermore, the voxels in the boundary region are more challenging to differentiate than those in the interior. In this paper, we propose HASSC approach to train the semantic scene completion model with hardness-aware design. The global hardness from the network optimization process is defined for dynamical hard voxel selection. Then, the local hardness with geometric anisotropy is adopted for voxel-wise refinement. Besides, self-distillation strategy is introduced to make training process stable and consistent. Extensive experiments show that our HASSC scheme can effectively promote the accuracy of the baseline model without incurring the extra inference cost. Source code is available at: https://github.com/songw-zju/HASSC.