Zobrazeno 1 - 10
of 2 016
pro vyhledávání: '"LIU, ZIWEI"'
We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects. Unlike existing methods that rely on complex pipelines or case-specific optimizations, Material Anything offe
Externí odkaz:
http://arxiv.org/abs/2411.15138
Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an initial step t
Externí odkaz:
http://arxiv.org/abs/2411.14982
Autor:
Dong, Yuhao, Liu, Zuyan, Sun, Hai-Long, Yang, Jingkang, Hu, Winston, Rao, Yongming, Liu, Ziwei
Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning, high-quality long-
Externí odkaz:
http://arxiv.org/abs/2411.14432
Autor:
Huang, Ziqi, Zhang, Fan, Xu, Xiaojie, He, Yinan, Yu, Jiashuo, Dong, Ziyue, Ma, Qianli, Chanpaisit, Nattapol, Si, Chenyang, Jiang, Yuming, Wang, Yaohui, Chen, Xinyuan, Chen, Ying-Cong, Wang, Limin, Lin, Dahua, Qiao, Yu, Liu, Ziwei
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human pe
Externí odkaz:
http://arxiv.org/abs/2411.13503
In this paper, we propose a novel transmissive reconfigurable intelligent surface (TRIS) transceiver-empowered distributed cooperative integrated sensing and communication (ISAC) network to enhance coverage as well as to enhance wireless environment
Externí odkaz:
http://arxiv.org/abs/2411.10960
Retrieval-augmented generation (RAG) has shown impressive capability in providing reliable answer predictions and addressing hallucination problems. A typical RAG implementation uses powerful retrieval models to extract external information and large
Externí odkaz:
http://arxiv.org/abs/2411.07021
Autor:
Cheng, Wei, Mu, Juncheng, Zeng, Xianfang, Chen, Xin, Pang, Anqi, Zhang, Chi, Wang, Zhibin, Fu, Bin, Yu, Gang, Liu, Ziwei, Pan, Liang
Texturing is a crucial step in the 3D asset production workflow, which enhances the visual appeal and diversity of 3D assets. Despite recent advancements in Text-to-Texture (T2T) generation, existing methods often yield subpar results, primarily due
Externí odkaz:
http://arxiv.org/abs/2411.02336
Virtual try-on (VTON) transfers a target clothing image to a reference person, where clothing fidelity is a key requirement for downstream e-commerce applications. However, existing VTON methods still fall short in high-fidelity try-on due to the con
Externí odkaz:
http://arxiv.org/abs/2411.01593
Autor:
Lv, Zhengyao, Si, Chenyang, Song, Junhao, Yang, Zhenyu, Qiao, Yu, Liu, Ziwei, Wong, Kwan-Yee K.
In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that \textit{di
Externí odkaz:
http://arxiv.org/abs/2410.19355
LiDAR scene generation has been developing rapidly recently. However, existing methods primarily focus on generating static and single-frame scenes, overlooking the inherently dynamic nature of real-world driving environments. In this work, we introd
Externí odkaz:
http://arxiv.org/abs/2410.18084