Zobrazeno 1 - 10
of 2 810
pro vyhledávání: '"Lu-Fan An"'
Autor:
Wu, Wei, Zheng, Kecheng, Ma, Shuailei, Lu, Fan, Guo, Yuxin, Zhang, Yifei, Chen, Wei, Guo, Qingpei, Shen, Yujun, Zha, Zheng-Jun
Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key reason causing such an issue is that the training images are usually pair
Externí odkaz:
http://arxiv.org/abs/2410.05249
Although recent efforts have extended Neural Radiance Fields (NeRF) into LiDAR point cloud synthesis, the majority of existing works exhibit a strong dependence on precomputed poses. However, point cloud registration methods struggle to achieve preci
Externí odkaz:
http://arxiv.org/abs/2407.05597
Collaborative perception is dedicated to tackling the constraints of single-agent perception, such as occlusions, based on the multiple agents' multi-view sensor inputs. However, most existing works assume an ideal condition that all agents' multi-vi
Externí odkaz:
http://arxiv.org/abs/2405.16868
Text-to-3D generation has achieved remarkable success via large-scale text-to-image diffusion models. Nevertheless, there is no paradigm for scaling up the methodology to urban scale. Urban scenes, characterized by numerous elements, intricate arrang
Externí odkaz:
http://arxiv.org/abs/2404.06780
Although neural radiance fields (NeRFs) have achieved triumphs in image novel view synthesis (NVS), LiDAR NVS remains largely unexplored. Previous LiDAR NVS methods employ a simple shift from image NVS methods while ignoring the dynamic nature and th
Externí odkaz:
http://arxiv.org/abs/2404.02742
Autor:
Zheng, Kecheng, Zhang, Yifei, Wu, Wei, Lu, Fan, Ma, Shuailei, Jin, Xin, Chen, Wei, Shen, Yujun
Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10 sentences),
Externí odkaz:
http://arxiv.org/abs/2403.17007
Autor:
Liu, Haotian, Qu, Sanqing, Lu, Fan, Bu, Zongtao, Roehrbein, Florian, Knoll, Alois, Chen, Guang
Event cameras can record scene dynamics with high temporal resolution, providing rich scene details for monocular depth estimation (MDE) even at low-level illumination. Therefore, existing complementary learning approaches for MDE fuse intensity info
Externí odkaz:
http://arxiv.org/abs/2402.18925
Full-spectrum out-of-distribution (F-OOD) detection aims to accurately recognize in-distribution (ID) samples while encountering semantic and covariate shifts simultaneously. However, existing out-of-distribution (OOD) detectors tend to overfit the c
Externí odkaz:
http://arxiv.org/abs/2312.01732
Outdoor LiDAR point clouds are typically large-scale and complexly distributed. To achieve efficient and accurate registration, emphasizing the similarity among local regions and prioritizing global local-to-local matching is of utmost importance, su
Externí odkaz:
http://arxiv.org/abs/2310.18874
Autor:
Lu, Fan, Meyn, Sean
The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of optimal c
Externí odkaz:
http://arxiv.org/abs/2309.05105