Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.23480 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916873395765248 |
|---|---|
| author | Lee, Donghyun Jeong, Dawoon Lee, Jae W. Yoon, Hongil |
| author_facet | Lee, Donghyun Jeong, Dawoon Lee, Jae W. Yoon, Hongil |
| contents | Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique that leverages the predictable distance trend between sampled points during farthest point sampling. By predicting the distance curve, we can efficiently identify subsequent sample points without exhaustively computing all pairwise distances. Our proposal substantially accelerates farthest point sampling and neighbor search operations while preserving sampling quality and model performance. By integrating FastPoint into state-of-the-art 3D point cloud models, we achieve 2.55x end-to-end speedup on NVIDIA RTX 3090 GPU without sacrificing accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23480 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction Lee, Donghyun Jeong, Dawoon Lee, Jae W. Yoon, Hongil Computer Vision and Pattern Recognition Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique that leverages the predictable distance trend between sampled points during farthest point sampling. By predicting the distance curve, we can efficiently identify subsequent sample points without exhaustively computing all pairwise distances. Our proposal substantially accelerates farthest point sampling and neighbor search operations while preserving sampling quality and model performance. By integrating FastPoint into state-of-the-art 3D point cloud models, we achieve 2.55x end-to-end speedup on NVIDIA RTX 3090 GPU without sacrificing accuracy. |
| title | FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.23480 |