Zobrazeno 1 - 10
of 872
pro vyhledávání: '"Chen, Xinyuan"'
Existing single image-to-3D creation methods typically involve a two-stage process, first generating multi-view images, and then using these images for 3D reconstruction. However, training these two stages separately leads to significant data bias in
Externí odkaz:
http://arxiv.org/abs/2406.03184
Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models. However, these methods lack multi-view spatial-temporal modeling and encounter challenges in integrating diverse prior knowledge fro
Externí odkaz:
http://arxiv.org/abs/2405.20674
Autor:
Chen, Xinyuan, Li, Fan
Principal stratification is a popular framework for causal inference in the presence of an intermediate outcome. While the principal average treatment effects have traditionally been the default target of inference, it may not be sufficient when the
Externí odkaz:
http://arxiv.org/abs/2403.08927
In longitudinal observational studies with a time-to-event outcome, a common objective in causal analysis is to estimate the causal survival curve under hypothetical intervention scenarios within the study cohort. The g-formula is a particularly usef
Externí odkaz:
http://arxiv.org/abs/2402.02306
Autor:
Ma, Xin, Wang, Yaohui, Jia, Gengyun, Chen, Xinyuan, Liu, Ziwei, Li, Yuan-Fang, Chen, Cunjian, Qiao, Yu
We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In orde
Externí odkaz:
http://arxiv.org/abs/2401.03048
We propose a two-stage estimation procedure for a copula-based model with semi-competing risks data, where the non-terminal event is subject to dependent censoring by the terminal event, and both events are subject to independent censoring. Under a c
Externí odkaz:
http://arxiv.org/abs/2312.14013
Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we propose Diff
Externí odkaz:
http://arxiv.org/abs/2312.12232
Autor:
Huang, Zehuan, Wen, Hao, Dong, Junting, Wang, Yaohui, Li, Yangguang, Chen, Xinyuan, Cao, Yan-Pei, Liang, Ding, Qiao, Yu, Dai, Bo, Sheng, Lu
Generating multiview images from a single view facilitates the rapid generation of a 3D mesh conditioned on a single image. Recent methods that introduce 3D global representation into diffusion models have shown the potential to generate consistent m
Externí odkaz:
http://arxiv.org/abs/2312.06725
Autor:
Chen, Xinyuan, Wang, Yaohui, Zhang, Lingjun, Zhuang, Shaobin, Ma, Xin, Yu, Jiashuo, Wang, Yali, Lin, Dahua, Qiao, Yu, Liu, Ziwei
Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level") depicting a single scene. To deliver a coherent long video ("story-level"), it
Externí odkaz:
http://arxiv.org/abs/2310.20700
Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a traini
Externí odkaz:
http://arxiv.org/abs/2310.07697