Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

arXiv:2311.18113v2 Announce Type: replace
Abstract: With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose to explore foundation models for the task of keypoint detection on 3D shapes. A unique characteristic of keypoint detection is that it requires semantic and geometric awareness while demanding high localization accuracy. To address this problem, we propose, first, to back-project features from large pre-trained 2D …

abstract arxiv become computing computing resources cs.cv cs.gr dataset detection explore features few-shot foundation growth keypoint detection nlp popular resources tasks type vision work