# 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2311.15605 · HTML: https://mlsanity.com/paper/2311.15605/

## Key facts

- Cited by 6 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 33 of its 46 references that are in the map.
- First posted on arXiv 27 Nov 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 33)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2012.04934/) (2020)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Scribble-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2203.08537/) (2022)
- [Weakly Supervised 3D Object Detection from Lidar Point Cloud](https://mlsanity.com/paper/2007.11901/) (2020)
- [Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2012.10782/) (2020)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2106.15277/) (2021)
- [SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network](https://mlsanity.com/paper/2104.07861/) (2021)
- [LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks](https://mlsanity.com/paper/1809.07941/) (2018)
- [LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2108.07511/) (2021)

## Built on by (most cited first, 6 of 6)

- [MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2408.16478/) (2024)
- [HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving](https://mlsanity.com/paper/2503.17752/) (2025)
- [Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2408.11280/) (2024)
- [Bayesian Self-Training for Semi-Supervised 3D Segmentation](https://mlsanity.com/paper/2409.08102/) (2024)
- [Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2603.06374/) (2026)
- [RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2604.06825/) (2026)

## Abstract (arXiv)

As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised training. However these methods continue to show weak boundary estimation and high false negative rates for small objects and distant sparse regions. We argue that such weaknesses can be compensated by using RGB images which provide a denser representation of the scene. We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. We further utilize a one-way contrastive learning scheme alongside a novel mixing strategy called FOVMix, to combat the horizontal field-of-view mismatch between the two sensors and enhance the effects of image guidance. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points, while introducing no additional annotation burden or computational/memory cost during inference. Furthermore, we show that our contributions also prove effective for semi-supervised training, where IGNet claims state-of-the-art results on both ScribbleKITTI and SemanticKITTI.