Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Zhou, Kaichen"'
Recent advancements in industrial anomaly detection have been hindered by the lack of realistic datasets that accurately represent real-world conditions. Existing algorithms are often developed and evaluated using idealized datasets, which deviate si
Externí odkaz:
http://arxiv.org/abs/2410.00713
Location information is pivotal for the automation and intelligence of terminal devices and edge-cloud IoT systems, such as autonomous vehicles and augmented reality. However, achieving reliable positioning across diverse IoT applications remains cha
Externí odkaz:
http://arxiv.org/abs/2408.09680
Despite the photorealistic novel view synthesis (NVS) performance achieved by the original 3D Gaussian splatting (3DGS), its rendering quality significantly degrades with sparse input views. This performance drop is mainly caused by the limited numbe
Externí odkaz:
http://arxiv.org/abs/2408.00254
Autor:
Xia, Yan, Ding, Ran, Qin, Ziyuan, Zhan, Guanqi, Zhou, Kaichen, Yang, Long, Dong, Hao, Cremers, Daniel
Recent advances in predicting 6D grasp poses from a single depth image have led to promising performance in robotic grasping. However, previous grasping models face challenges in cluttered environments where nearby objects impact the target object's
Externí odkaz:
http://arxiv.org/abs/2407.06168
Autor:
Xiong, Chuyan, Shen, Chengyu, Li, Xiaoqi, Zhou, Kaichen, Liu, Jiaming, Wang, Ruiping, Dong, Hao
The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects. Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aim
Externí odkaz:
http://arxiv.org/abs/2406.11548
Autor:
Liu, Jiaming, Liu, Mengzhen, Wang, Zhenyu, Lee, Lily, Zhou, Kaichen, An, Pengju, Yang, Senqiao, Zhang, Renrui, Guo, Yandong, Zhang, Shanghang
A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing robot Multimodal Large Language Models (MLLMs) can handle a range of basic tasks, they still face challenges in two a
Externí odkaz:
http://arxiv.org/abs/2406.04339
Autor:
Zhou, Kaichen
This paper addresses the challenge of reconstructing surfaces from sparse view inputs, where ambiguity and occlusions due to missing information pose significant hurdles. We present a novel approach, named EpiS, that incorporates Epipolar information
Externí odkaz:
http://arxiv.org/abs/2406.04301
Autor:
Liu, Jiaming, Li, Chenxuan, Wang, Guanqun, Lee, Lily, Zhou, Kaichen, Chen, Sixiang, Xiong, Chuyan, Ge, Jiaxin, Zhang, Renrui, Zhang, Shanghang
Robot manipulation policies have shown unsatisfactory action performance when confronted with novel task or object instances. Hence, the capability to automatically detect and self-correct failure action is essential for a practical robotic system. R
Externí odkaz:
http://arxiv.org/abs/2405.17418
Autonomous assembly in robotics and 3D vision presents significant challenges, particularly in ensuring assembly correctness. Presently, predominant methods such as MEPNet focus on assembling components based on manually provided images. However, the
Externí odkaz:
http://arxiv.org/abs/2403.18195
Despite the advancements in deep learning for camera relocalization tasks, obtaining ground truth pose labels required for the training process remains a costly endeavor. While current weakly supervised methods excel in lightweight label generation,
Externí odkaz:
http://arxiv.org/abs/2403.15272