# Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving

arXiv: https://arxiv.org/abs/2310.08826 · HTML: https://mlsanity.com/paper/2310.08826/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [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)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2012.04934/) (2020)
- [LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception](https://mlsanity.com/paper/2209.09385/) (2022)
- [Sparse 3D convolutional neural networks](https://mlsanity.com/paper/1505.02890/) (2015)
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2303.08600/) (2023)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2106.15277/) (2021)
- [CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2207.12691/) (2022)
- [RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/1906.00208/) (2019)
- [GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2207.02605/) (2022)
- [LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2108.07511/) (2021)
- [FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data](https://mlsanity.com/paper/1912.08487/) (2019)
- [CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation](https://mlsanity.com/paper/2204.09914/) (2022)
- [Deep Learning for 3D Point Cloud Understanding: A Survey](https://mlsanity.com/paper/2009.08920/) (2020)
- [Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation](https://mlsanity.com/paper/2207.04673/) (2022)

## Built on by (most cited first, 2 of 2)

- [Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives](https://mlsanity.com/paper/2402.02968/) (2024)
- [LVIC: Multi-modality segmentation by Lifting Visual Info as Cue](https://mlsanity.com/paper/2403.05159/) (2024)

## Abstract (arXiv)

LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key challenges: 1) difficulty with efficient deployment and real-time execution; and 2) drastic performance degradation under weak calibration between LiDAR and cameras. To address these challenges, we propose CPGNet-LCF, a new multi-modal fusion framework extending the LiDAR-only CPGNet. CPGNet-LCF solves the first challenge by inheriting the easy deployment and real-time capabilities of CPGNet. For the second challenge, we introduce a novel weak calibration knowledge distillation strategy during training to improve the robustness against the weak calibration. CPGNet-LCF achieves state-of-the-art performance on the nuScenes and SemanticKITTI benchmarks. Remarkably, it can be easily deployed to run in 20ms per frame on a single Tesla V100 GPU using TensorRT TF16 mode. Furthermore, we benchmark performance over four weak calibration levels, demonstrating the robustness of our proposed approach.