Risultati della ricerca - Xu, Tianshuo

Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon di Xu, Tianshuo, Mi, Peng, Wang, Ruilin, Chen, Yingcong

Testo

From Bird's-Eye to Street View: Crafting Diverse and Condition-Aligned Images with Latent Diffusion Model di Xu, Xiaojie, Xu, Tianshuo, Ma, Fulong, Chen, Yingcong

Testo

Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics di Xu, Tianshuo, Chen, Zhifei, Wu, Leyi, Lu, Hao, Chen, Ying-cong

Testo

CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning di Xu, Tianshuo, Hong, Tiantian, Chen, Zhifei, Chao, Fei, Chen, Ying-cong

Testo

Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models di Xu, Tianshuo, Lu, Hao, Yan, Xu, Cai, Yingjie, Liu, Bingbing, Chen, Yingcong

Testo

LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation di Jiang, Bo, Meng, Depu, Hu, Yihan, Xie, Yichen, Xu, Tianshuo, Zhan, Wei

Testo

UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy di Xu, Tianshuo, Wang, Kai, Chen, Zhifei, Wu, Leyi, Wen, Tianshui, Chao, Fei, Chen, Ying-Cong

Testo

Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization di Xu, Tianshuo, Li, Lijiang, Mi, Peng, Zheng, Xiawu, Chao, Fei, Ji, Rongrong, Tian, Yonghong, Shen, Qiang

Testo

Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generation di Xu, Tianshuo, Chen, Zhifei, Wu, Leyi, Lu, Hao, Chen, Yuying, Jiang, Lihui, Liu, Bingbing, Chen, Yingcong

Testo

SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes di Herau, Quentin, Xu, Tianshuo, Meng, Depu, Yang, Jiezhi, Peng, Chensheng, Sherk, Spencer, Hu, Yihan, Zhan, Wei

Testo

Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution di Xu, Tianshuo, Xie, Yichen, Meng, Depu, Peng, Chensheng, Herau, Quentin, Jiang, Bo, Hu, Yihan, Zhan, Wei

Testo

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving di Lu, Hao, Xu, Tianshuo, Zheng, Wenzhao, Zhang, Yunpeng, Zhan, Wei, Du, Dalong, Tomizuka, Masayoshi, Keutzer, Kurt, Chen, Yingcong

Testo

STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding di Chen, Zhifei, Xu, Tianshuo, Wu, Leyi, Wang, Luozhou, Yan, Dongyu, You, Zihan, Luo, Wenting, Zhang, Guo, Chen, Yingcong

Testo

Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion di Chen, Zhifei, Xu, Tianshuo, Ge, Wenhang, Wu, Leyi, Yan, Dongyu, He, Jing, Wang, Luozhou, Zeng, Lu, Zhang, Shunsi, Chen, Yingcong

Testo

FlexPainter: Flexible and Multi-View Consistent Texture Generation di Yan, Dongyu, Wu, Leyi, Lin, Jiantao, Wang, Luozhou, Xu, Tianshuo, Chen, Zhifei, Yang, Zhen, Xu, Lie, Zhang, Shunsi, Chen, Yingcong

Testo

A Mechanistic View on Video Generation as World Models: State and Dynamics di Wang, Luozhou, Chen, Zhifei, Du, Yihua, Yan, Dongyu, Ge, Wenhang, Shen, Guibao, Xu, Xinli, Wu, Leyi, Chen, Man, Xu, Tianshuo, Ren, Peiran, Tao, Xin, Wan, Pengfei, Chen, Ying-Cong

Testo

RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes di Wu, Leyi, Zhao, Yifan, Zhang, Jinjie, Chen, Suzeyu, Chen, Wosong, Chen, Zhifei, Xu, Tianshuo, He, Qingchun, Hu, Hongxin, Huang, Haojian, Wei, Yangkai, Li, Wenqian, Li, Yinchuan, Chen, Ying-Cong

Testo