# OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2403.14418 · HTML: https://mlsanity.com/paper/2403.14418/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 80 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [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)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)

## Built on by (most cited first, 30 of 44)

- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging](https://mlsanity.com/paper/2602.08024/) (2026)
- [LitePT: Lighter Yet Stronger Point Transformer](https://mlsanity.com/paper/2512.13689/) (2025)
- [Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior](https://mlsanity.com/paper/2512.06866/) (2025)
- [LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2506.07857/) (2025)
- [Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds](https://mlsanity.com/paper/2502.20316/) (2025)
- [Typicalness-Aware Learning for Failure Detection](https://mlsanity.com/paper/2411.01981/) (2024)
- [UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting](https://mlsanity.com/paper/2506.09952/) (2025)
- [BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis](https://mlsanity.com/paper/2503.12539/) (2025)
- [Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM](https://mlsanity.com/paper/2606.26120/) (2026)
- [Terra: Explorable Native 3D World Model with Point Latents](https://mlsanity.com/paper/2510.14977/) (2025)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion](https://mlsanity.com/paper/2506.15610/) (2025)
- [TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network](https://mlsanity.com/paper/2508.14373/) (2025)
- [3DAeroRelief: The first 3D Benchmark UAV Dataset for Post-Disaster Assessment](https://mlsanity.com/paper/2509.11097/) (2025)
- [OpenTrack3D: Towards Accurate and Generalizable Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2512.03532/) (2025)
- [CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios](https://mlsanity.com/paper/2508.09470/) (2025)
- [PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting](https://mlsanity.com/paper/2605.11520/) (2026)
- [FFNet: MetaMixer-based Efficient Convolutional Mixer Design](https://mlsanity.com/paper/2406.02021/) (2024)
- [Exploring contextual modeling with linear complexity for point cloud segmentation](https://mlsanity.com/paper/2410.21211/) (2024)
- [Enhancing point cloud analysis via neighbor aggregation correction based on cross-stage structure correlation](https://mlsanity.com/paper/2506.15160/) (2025)
- [PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks](https://mlsanity.com/paper/2508.10557/) (2025)
- [Comprehensive Assessment of LiDAR Evaluation Metrics: A Comparative Study Using Simulated and Real Data](https://mlsanity.com/paper/2511.02994/) (2025)
- [Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and Methodology](https://mlsanity.com/paper/2511.05853/) (2025)
- [3D Semantic Segmentation for Post-Disaster Assessment](https://mlsanity.com/paper/2512.24593/) (2025)
- [RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings](https://mlsanity.com/paper/2605.10706/) (2026)
- [Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation](https://mlsanity.com/paper/2407.15282/) (2024)
- [Density-aware global-local attention network for point cloud segmentation](https://mlsanity.com/paper/2412.00489/) (2024)
- [Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement](https://mlsanity.com/paper/2504.01449/) (2025)

## Abstract (arXiv)

The booming of 3D recognition in the 2020s began with the introduction of point cloud transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models, especially in 3D semantic segmentation. However, sparse CNNs are still valuable networks, due to their efficiency treasure, and ease of application. In this work, we reexamine the design distinctions and test the limits of what a sparse CNN can achieve. We discover that the key credit to the performance difference is adaptivity. Specifically, we propose two key components, i.e., adaptive receptive fields (spatially) and adaptive relation, to bridge the gap. This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost. Without any self-attention modules, OA-CNNs favorably surpass point transformers in terms of accuracy in both indoor and outdoor scenes, with much less latency and memory cost. Notably, it achieves 76.1%, 78.9%, and 70.6% mIoU on ScanNet v2, nuScenes, and SemanticKITTI validation benchmarks respectively, while maintaining at most 5x better speed than transformer counterparts. This revelation highlights the potential of pure sparse CNNs to outperform transformer-related networks.