Yu-Qi Yang

TL;DR: In this article , the authors propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations through a novel attention-based decoder which is independent of the encoder design.

TL;DR: In this paper , a semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data is proposed, where a multilevel consistency loss is used to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point level, part level, and hierarchical level.

TL;DR: A simple baseline could achieve state-of-the-art performance in detecting artefacts in endoscopy using faster region-based convolutional neural networks and the combination of EfficientDet-D2 with suitable data augmentation and pre-trained parameters during fine-tuning training to detect the artefacts.

TL;DR: Swin3D++ is proposed, an enhanced architecture based on Swin3D for efficient pretraining on multi-source 3D point clouds that surpasses the state-of-the-art 3D pretraining methods on typical indoor scene understanding tasks and devise a simple source-augmentation strategy to increase the pretraining data scale and facilitate supervised pretraining.