Zobrazeno 1 - 10
of 77
pro vyhledávání: '"SUN, Keqiang"'
Autor:
Li, Yijin, Shen, Yichen, Huang, Zhaoyang, Chen, Shuo, Bian, Weikang, Shi, Xiaoyu, Wang, Fu-Yun, Sun, Keqiang, Bao, Hujun, Cui, Zhaopeng, Zhang, Guofeng, Li, Hongsheng
Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as opti
Externí odkaz:
http://arxiv.org/abs/2410.20451
Autor:
Ma, Yuhang, Xu, Wenting, Zhao, Chaoyi, Sun, Keqiang, Jin, Qinfeng, Zhao, Zeng, Fan, Changjie, Hu, Zhipeng
Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consist
Externí odkaz:
http://arxiv.org/abs/2409.19624
Autor:
Sun, Keqiang, Jourabloo, Amin, Bhalodia, Riddhish, Meshry, Moustafa, Rong, Yu, Yang, Zhengyu, Nguyen-Phuoc, Thu, Haene, Christian, Xu, Jiu, Johnson, Sam, Li, Hongsheng, Bouaziz, Sofien
Photo-realistic and controllable 3D avatars are crucial for various applications such as virtual and mixed reality (VR/MR), telepresence, gaming, and film production. Traditional methods for avatar creation often involve time-consuming scanning and r
Externí odkaz:
http://arxiv.org/abs/2408.13674
Autor:
Wang, Fu-Yun, Huang, Zhaoyang, Bergman, Alexander William, Shen, Dazhong, Gao, Peng, Lingelbach, Michael, Sun, Keqiang, Bian, Weikang, Song, Guanglu, Liu, Yu, Li, Hongsheng, Wang, Xiaogang
The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models. However, its application to high-resolution, text-conditioned image generation in the latent space (a.k.a., LCM) remains unsatisfact
Externí odkaz:
http://arxiv.org/abs/2405.18407
Autor:
Wu, Xiaoshi, Hao, Yiming, Zhang, Manyuan, Sun, Keqiang, Huang, Zhaoyang, Song, Guanglu, Liu, Yu, Li, Hongsheng
Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of a text-to-
Externí odkaz:
http://arxiv.org/abs/2405.00760
Autor:
Li, Sicheng, Sun, Keqiang, Lai, Zhixin, Wu, Xiaoshi, Qiu, Feng, Xie, Haoran, Miyata, Kazunori, Li, Hongsheng
The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reasons, ambiguous condition input and inadequate condition guidance over s
Externí odkaz:
http://arxiv.org/abs/2403.18417
Autor:
Wang, Fu-Yun, Huang, Zhaoyang, Bian, Weikang, Shi, Xiaoyu, Sun, Keqiang, Song, Guanglu, Liu, Yu, Li, Hongsheng
This paper introduces an effective method for computation-efficient personalized style video generation without requiring access to any personalized video data. It reduces the necessary generation time of similarly sized video diffusion models from 2
Externí odkaz:
http://arxiv.org/abs/2402.00769
We introduce a new method for learning a generative model of articulated 3D animal motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion synthesis, our model requires no pose annotations or parametric shape models for tr
Externí odkaz:
http://arxiv.org/abs/2312.13604
Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. In this paper, we identify several crit
Externí odkaz:
http://arxiv.org/abs/2309.14616
Autor:
Sun, Keqiang, Pan, Junting, Ge, Yuying, Li, Hao, Duan, Haodong, Wu, Xiaoshi, Zhang, Renrui, Zhou, Aojun, Qin, Zipeng, Wang, Yi, Dai, Jifeng, Qiao, Yu, Wang, Limin, Li, Hongsheng
While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehend generated images remains uncertain. Synthetic images, in comparison
Externí odkaz:
http://arxiv.org/abs/2307.00716