# Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

arXiv: https://arxiv.org/abs/2007.16100 · HTML: https://mlsanity.com/paper/2007.16100/

## Key facts

- Cited by 423 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 30 of 423)

- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023)
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2206.05737/) (2022)
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2103.12978/) (2021)
- [Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking](https://mlsanity.com/paper/2109.03805/) (2021)
- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://mlsanity.com/paper/2103.15297/) (2021)
- [Robo3D: Towards Robust and Reliable 3D Perception against Corruptions](https://mlsanity.com/paper/2303.17597/) (2023)
- [Rethinking Range View Representation for LiDAR Segmentation](https://mlsanity.com/paper/2303.05367/) (2023)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://mlsanity.com/paper/2103.14962/) (2021)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2203.11283/) (2022)
- [QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits](https://mlsanity.com/paper/2107.10845/) (2021)
- [SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model](https://mlsanity.com/paper/2403.13064/) (2024)
- [TPCN: Temporal Point Cloud Networks for Motion Forecasting](https://mlsanity.com/paper/2103.03067/) (2021)
- [3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2209.15076/) (2022)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)

## Abstract (arXiv)

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due to the low-resolution voxelization and aggressive downsampling. To this end, we propose Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch. With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes. To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network architecture over this diverse design space efficiently and effectively. Experimental results validate that the resulting SPVNAS model is fast and accurate: it outperforms the state-of-the-art MinkowskiNet by 3.3%, ranking 1st on the competitive SemanticKITTI leaderboard. It also achieves 8x computation reduction and 3x measured speedup over MinkowskiNet with higher accuracy. Finally, we transfer our method to 3D object detection, and it achieves consistent improvements over the one-stage detection baseline on KITTI.