Výsledky vyhledávání

Report

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything

Autor: Wei, Xiaobao, Zhang, Renrui, Wu, Jiarui, Liu, Jiaming, Lu, Ming, Guo, Yandong, Zhang, Shanghang

Neural 3D reconstruction from multi-view images has recently attracted increasing attention from the community. Existing methods normally learn a neural field for the whole scene, while it is still under-explored how to reconstruct a target object in

Externí odkaz: http://arxiv.org/abs/2309.12790

Zobrazit plný text záznamu

Report

PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers

Autor: Jia, Peidong, Liu, Jiaming, Yang, Senqiao, Wu, Jiarui, Xie, Xiaodong, Zhang, Shanghang

The Transformer-based detectors (i.e., DETR) have demonstrated impressive performance on end-to-end object detection. However, transferring DETR to different data distributions may lead to a significant performance degradation. Existing adaptation te

Externí odkaz: http://arxiv.org/abs/2307.00313

Zobrazit plný text záznamu

Report

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Autor: Yang, Senqiao, Wu, Jiarui, Liu, Jiaming, Li, Xiaoqi, Zhang, Qizhe, Pan, Mingjie, Gan, Yulu, Chen, Zehui, Zhang, Shanghang

The visual prompts have provided an efficient manner in addressing visual cross-domain problems. In previous works, Visual Domain Prompt (VDP) first introduces domain prompts to tackle the classification Test-Time Adaptation (TTA) problem by warping

Externí odkaz: http://arxiv.org/abs/2303.09792

Zobrazit plný text záznamu