Zobrazeno 1 - 10
of 9 864
pro vyhledávání: '"GUO, Yuan"'
Existing multi-view image generation methods often make invasive modifications to pre-trained text-to-image (T2I) models and require full fine-tuning, leading to (1) high computational costs, especially with large base models and high-resolution imag
Externí odkaz:
http://arxiv.org/abs/2412.03632
Autor:
Huang, Zehuan, Guo, Yuan-Chen, An, Xingqiao, Yang, Yunhan, Li, Yangguang, Zou, Zi-Xin, Liang, Ding, Liu, Xihui, Cao, Yan-Pei, Sheng, Lu
This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage object-by-object generati
Externí odkaz:
http://arxiv.org/abs/2412.03558
Decomposing physically-based materials from images into their constituent properties remains challenging, particularly when maintaining both computational efficiency and physical consistency. While recent diffusion-based approaches have shown promise
Externí odkaz:
http://arxiv.org/abs/2411.17515
Autor:
Yu, Xin, Yuan, Ze, Guo, Yuan-Chen, Liu, Ying-Tian, Liu, JianHui, Li, Yangguang, Cao, Yan-Pei, Liang, Ding, Qi, Xiaojuan
Publikováno v:
ACM Transactions on Graphics (TOG) 2024, Volume 43, Issue 6, Article No.: 213, Pages 1-14
While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work, we depart from the conventional approach of relying on
Externí odkaz:
http://arxiv.org/abs/2411.14740
Integrated sensing and communication (ISAC) is envisioned as a key technology for future sixth-generation (6G) networks. Classical ISAC system considering monostatic and/or bistatic settings will inevitably degrade both communication and sensing perf
Externí odkaz:
http://arxiv.org/abs/2411.09426
Autor:
Yang, Yunhan, Huang, Yukun, Guo, Yuan-Chen, Lu, Liangjun, Wu, Xiaoyang, Lam, Edmund Y., Cao, Yan-Pei, Liu, Xihui
3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge di
Externí odkaz:
http://arxiv.org/abs/2411.07184
Autor:
Sun, Jingxiang, Peng, Cheng, Shao, Ruizhi, Guo, Yuan-Chen, Zhao, Xiaochen, Li, Yangguang, Cao, Yanpei, Zhang, Bo, Liu, Yebin
We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming geometry sculpt
Externí odkaz:
http://arxiv.org/abs/2410.12928
Autor:
Zhi, Yuxing, Guo, Yuan, Yuan, Kai, Wang, Hesong, Xu, Heng, Yao, Haina, Yang, Albert C, Huang, Guangrui, Duan, Yuping
Background: Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. However, high-quality evidence is urgently needed on the potential and limitation of LLMs in providing accurate clinical decisio
Externí odkaz:
http://arxiv.org/abs/2409.14478
Real-world data often has a long-tailed distribution, where the scarcity of tail samples significantly limits the model's generalization ability. Denoising Diffusion Probabilistic Models (DDPM) are generative models based on stochastic differential e
Externí odkaz:
http://arxiv.org/abs/2409.14313
Autor:
Chern, Steffi, Hu, Zhulin, Yang, Yuqing, Chern, Ethan, Guo, Yuan, Jin, Jiahe, Wang, Binjie, Liu, Pengfei
Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has received relatively less attention. Dishonest behaviors in LLMs, such as sp
Externí odkaz:
http://arxiv.org/abs/2406.13261