# MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modeling

arXiv: https://arxiv.org/abs/2411.03672 · HTML: https://mlsanity.com/paper/2411.03672/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [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)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving](https://mlsanity.com/paper/2202.08449/) (2022)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving](https://mlsanity.com/paper/2005.03778/) (2020)
- [ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans](https://mlsanity.com/paper/1712.10215/) (2017)
- [S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds](https://mlsanity.com/paper/2012.09242/) (2020)
- [Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data](https://mlsanity.com/paper/2011.09141/) (2020)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2009.03456/) (2020)
- [Two Stream 3D Semantic Scene Completion](https://mlsanity.com/paper/1804.03550/) (2018)
- [Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer](https://mlsanity.com/paper/2205.13947/) (2022)
- [Camera-based 3D Semantic Scene Completion with Sparse Guidance Network](https://mlsanity.com/paper/2312.05752/) (2023)
- [Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds](https://mlsanity.com/paper/2109.11453/) (2021)
- [HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving](https://mlsanity.com/paper/2401.03160/) (2024)
- [Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation](https://mlsanity.com/paper/2309.00121/) (2023)
- [DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception](https://mlsanity.com/paper/2310.08117/) (2023)

## Built on by (most cited first, 4 of 4)

- [CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models](https://mlsanity.com/paper/2502.15119/) (2025)
- [VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving](https://mlsanity.com/paper/2505.16377/) (2025)
- [SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding](https://mlsanity.com/paper/2508.06763/) (2025)
- [Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving](https://mlsanity.com/paper/2604.03497/) (2026)

## Abstract (arXiv)

Semantic scene completion (SSC) is essential for achieving comprehensive perception in autonomous driving systems. However, existing SSC methods often overlook the high deployment costs in real-world applications. Traditional architectures, such as 3D Convolutional Neural Networks (3D CNNs) and self-attention mechanisms, face challenges in efficiently capturing long-range dependencies within 3D voxel grids, limiting their effectiveness. To address these issues, we introduce MetaSSC, a novel meta-learning-based framework for SSC that leverages deformable convolution, large-kernel attention, and the Mamba (D-LKA-M) model. Our approach begins with a voxel-based semantic segmentation (SS) pretraining task, aimed at exploring the semantics and geometry of incomplete regions while acquiring transferable meta-knowledge. Using simulated cooperative perception datasets, we supervise the perception training of a single vehicle using aggregated sensor data from multiple nearby connected autonomous vehicles (CAVs), generating richer and more comprehensive labels. This meta-knowledge is then adapted to the target domain through a dual-phase training strategy that does not add extra model parameters, enabling efficient deployment. To further enhance the model's capability in capturing long-sequence relationships within 3D voxel grids, we integrate Mamba blocks with deformable convolution and large-kernel attention into the backbone network. Extensive experiments demonstrate that MetaSSC achieves state-of-the-art performance, significantly outperforming competing models while also reducing deployment costs.