Papers Training-free 3D Part Segmentation

“Training-free 3D Part Segmentation” 태그가 달린 논문 3편 · 필터 해제

Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

2023-03-14 · Renrui Zhang, Liuhui Wang, Ziyu Guo, Yali Wang 외

We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-NN), and pooling operations, with trigon…

3D Point Cloud Classification All Supervised Only 3D Point Cloud Classification Training-free 3D Part Segmentation+1

PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

2022-11-21 · ICCV 2023 1 · Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo 외

Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classific…

3D Classification 3D Object Detection 3D Open-Vocabulary Instance Segmentation 3D Part Segmentation+10

PointCLIP: Point Cloud Understanding by CLIP

2021-12-04 · CVPR 2022 1 · Renrui Zhang, Ziyu Guo, Wei zhang, Kunchang Li 외

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in …

3D Open-Vocabulary Instance Segmentation Few-Shot Learning Open Vocabulary Object Detection Training-free 3D Part Segmentation+5