# PointAcc: Efficient Point Cloud Accelerator

arXiv: https://arxiv.org/abs/2110.07600 · HTML: https://mlsanity.com/paper/2110.07600/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2021.

## Built on by (most cited first, 24 of 24)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [TorchSparse: Efficient Point Cloud Inference Engine](https://mlsanity.com/paper/2204.10319/) (2022)
- [TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs](https://mlsanity.com/paper/2311.12862/) (2023)
- [Transformer-QEC: Quantum Error Correction Code Decoding with Transferable Transformers](https://mlsanity.com/paper/2311.16082/) (2023)
- [Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection](https://mlsanity.com/paper/2307.08209/) (2023)
- [SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving](https://mlsanity.com/paper/2305.07522/) (2023)
- [Sparse Refinement for Efficient High-Resolution Semantic Segmentation](https://mlsanity.com/paper/2407.19014/) (2024)
- [Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection](https://mlsanity.com/paper/2408.13798/) (2024)
- [Applying Plain Transformers to Real-World Point Clouds](https://mlsanity.com/paper/2303.00086/) (2023)
- [Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network](https://mlsanity.com/paper/2306.09552/) (2023)
- [Minuet: Accelerating 3D Sparse Convolutions on GPUs](https://mlsanity.com/paper/2401.06145/) (2023)
- [GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA](https://mlsanity.com/paper/2404.07188/) (2024)
- [GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization](https://mlsanity.com/paper/2303.16459/) (2023)
- [LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications](https://mlsanity.com/paper/2509.12053/) (2025)
- [HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA](https://mlsanity.com/paper/2512.22139/) (2025)
- [NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation](https://mlsanity.com/paper/2602.00542/) (2026)
- [2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction](https://mlsanity.com/paper/2603.19964/) (2026)
- [Random resistive memory-based deep extreme point learning machine for unified visual processing](https://mlsanity.com/paper/2312.09262/) (2023)
- [NVR: Vector Runahead on NPUs for Sparse Memory Access](https://mlsanity.com/paper/2502.13873/) (2025)
- [FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing](https://mlsanity.com/paper/2511.07665/) (2025)
- [Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks](https://mlsanity.com/paper/2511.20834/) (2025)
- [PointCNN++: Performant Convolution on Native Points](https://mlsanity.com/paper/2511.23227/) (2025)
- [FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching](https://mlsanity.com/paper/2604.17720/) (2026)
- [RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruning](https://mlsanity.com/paper/2606.06255/) (2026)

## Abstract (arXiv)

Deep learning on point clouds plays a vital role in a wide range of applications such as autonomous driving and AR/VR. These applications interact with people in real-time on edge devices and thus require low latency and low energy. Compared to projecting the point cloud to 2D space, directly processing the 3D point cloud yields higher accuracy and lower #MACs. However, the extremely sparse nature of point cloud poses challenges to hardware acceleration. For example, we need to explicitly determine the nonzero outputs and search for the nonzero neighbors (mapping operation), which is unsupported in existing accelerators. Furthermore, explicit gather and scatter of sparse features are required, resulting in large data movement overhead. In this paper, we comprehensively analyze the performance bottleneck of modern point cloud networks on CPU/GPU/TPU. To address the challenges, we then present PointAcc, a novel point cloud deep learning accelerator. PointAcc maps diverse mapping operations onto one versatile ranking-based kernel, streams the sparse computation with configurable caching, and temporally fuses consecutive dense layers to reduce the memory footprint. Evaluated on 8 point cloud models across 4 applications, PointAcc achieves 3.7X speedup and 22X energy savings over RTX 2080Ti GPU. Co-designed with light-weight neural networks, PointAcc rivals the prior accelerator Mesorasi by 100X speedup with 9.1% higher accuracy running segmentation on the S3DIS dataset. PointAcc paves the way for efficient point cloud recognition.