Zobrazeno 1 - 10
of 343
pro vyhledávání: '"Vajda, Peter"'
Autor:
Zhang, Christina, Motwani, Simran, Yu, Matthew, Hou, Ji, Juefei-Xu, Felix, Tsai, Sam, Vajda, Peter, He, Zijian, Wang, Jialiang
Latent diffusion models (LDMs) have made significant advancements in the field of image generation in recent years. One major advantage of LDMs is their ability to operate in a compressed latent space, allowing for more efficient training and deploym
Externí odkaz:
http://arxiv.org/abs/2409.17565
Autor:
He, Zecheng, Sun, Bo, Juefei-Xu, Felix, Ma, Haoyu, Ramchandani, Ankit, Cheung, Vincent, Shah, Siddharth, Kalia, Anmol, Subramanyam, Harihar, Zareian, Alireza, Chen, Li, Jain, Ankit, Zhang, Ning, Zhang, Peizhao, Sumbaly, Roshan, Vajda, Peter, Sinha, Animesh
Diffusion models have demonstrated remarkable efficacy across various image-to-image tasks. In this research, we introduce Imagine yourself, a state-of-the-art model designed for personalized image generation. Unlike conventional tuning-based persona
Externí odkaz:
http://arxiv.org/abs/2409.13346
Autor:
Kohler, Jonas, Pumarola, Albert, Schönfeld, Edgar, Sanakoyeu, Artsiom, Sumbaly, Roshan, Vajda, Peter, Thabet, Ali
Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this work, we
Externí odkaz:
http://arxiv.org/abs/2405.05224
Autor:
Yan, David, Zhang, Winnie, Zhang, Luxin, Kalia, Anmol, Wang, Dingkang, Ramchandani, Ankit, Liu, Miao, Pumarola, Albert, Schoenfeld, Edgar, Blanchard, Elliot, Narni, Krishna, Luo, Yaqiao, Chen, Lawrence, Pang, Guan, Thabet, Ali, Vajda, Peter, Bearman, Amy, Yu, Licheng
We introduce animated stickers, a video diffusion model which generates an animation conditioned on a text prompt and static sticker image. Our model is built on top of the state-of-the-art Emu text-to-image model, with the addition of temporal layer
Externí odkaz:
http://arxiv.org/abs/2402.06088
Autor:
Liang, Feng, Wu, Bichen, Wang, Jialiang, Yu, Licheng, Li, Kunpeng, Zhao, Yinan, Misra, Ishan, Huang, Jia-Bin, Zhang, Peizhao, Vajda, Peter, Marculescu, Diana
Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video fr
Externí odkaz:
http://arxiv.org/abs/2312.17681
Autor:
Wu, Bichen, Chuang, Ching-Yao, Wang, Xiaoyan, Jia, Yichen, Krishnakumar, Kapil, Xiao, Tong, Liang, Feng, Yu, Licheng, Vajda, Peter
In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implic
Externí odkaz:
http://arxiv.org/abs/2312.13834
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has prese
Externí odkaz:
http://arxiv.org/abs/2312.11841
Autor:
Schult, Jonas, Tsai, Sam, Höllein, Lukas, Wu, Bichen, Wang, Jialiang, Ma, Chih-Yao, Li, Kunpeng, Wang, Xiaofang, Wimbauer, Felix, He, Zijian, Zhang, Peizhao, Leibe, Bastian, Vajda, Peter, Hou, Ji
Manually creating 3D environments for AR/VR applications is a complex process requiring expert knowledge in 3D modeling software. Pioneering works facilitate this process by generating room meshes conditioned on textual style descriptions. Yet, many
Externí odkaz:
http://arxiv.org/abs/2312.05208
Autor:
Zhang, Zhixing, Wu, Bichen, Wang, Xiaoyan, Luo, Yaqiao, Zhang, Luxin, Zhao, Yinan, Vajda, Peter, Metaxas, Dimitris, Yu, Licheng
Recent advances in diffusion models have successfully enabled text-guided image inpainting. While it seems straightforward to extend such editing capability into the video domain, there have been fewer works regarding text-guided video inpainting. Gi
Externí odkaz:
http://arxiv.org/abs/2312.03816
Autor:
Wimbauer, Felix, Wu, Bichen, Schoenfeld, Edgar, Dai, Xiaoliang, Hou, Ji, He, Zijian, Sanakoyeu, Artsiom, Zhang, Peizhao, Tsai, Sam, Kohler, Jonas, Rupprecht, Christian, Cremers, Daniel, Vajda, Peter, Wang, Jialiang
Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-t
Externí odkaz:
http://arxiv.org/abs/2312.03209