Zobrazeno 1 - 10
of 102
pro vyhledávání: '"Barnes, Connelly"'
Autor:
Kang, Minguk, Zhang, Richard, Barnes, Connelly, Paris, Sylvain, Kwak, Suha, Park, Jaesik, Shechtman, Eli, Zhu, Jun-Yan, Park, Taesung
We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image
Externí odkaz:
http://arxiv.org/abs/2405.05967
Autor:
Zhang, Lingzhi, Xu, Zhengjie, Barnes, Connelly, Zhou, Yuqian, Liu, Qing, Zhang, He, Amirghodsi, Sohrab, Lin, Zhe, Shechtman, Eli, Shi, Jianbo
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual correction. In th
Externí odkaz:
http://arxiv.org/abs/2310.05590
Autor:
Huynh, Chuong, Zhou, Yuqian, Lin, Zhe, Barnes, Connelly, Shechtman, Eli, Amirghodsi, Sohrab, Shrivastava, Abhinav
In photo editing, it is common practice to remove visual distractions to improve the overall image quality and highlight the primary subject. However, manually selecting and removing these small and dense distracting regions can be a laborious and ti
Externí odkaz:
http://arxiv.org/abs/2305.17624
Autor:
Chiu, Mang Tik, Zhang, Xuaner, Wei, Zijun, Zhou, Yuqian, Shechtman, Eli, Barnes, Connelly, Lin, Zhe, Kainz, Florian, Amirghodsi, Sohrab, Shi, Humphrey
Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos wher
Externí odkaz:
http://arxiv.org/abs/2304.00221
Autor:
Zheng, Haitian, Lin, Zhe, Lu, Jingwan, Cohen, Scott, Shechtman, Eli, Barnes, Connelly, Zhang, Jianming, Liu, Qing, Zhou, Yuqian, Amirghodsi, Sohrab, Luo, Jiebo
Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to hallucinate
Externí odkaz:
http://arxiv.org/abs/2212.06310
Autor:
Zhang, Lingzhi, Barnes, Connelly, Wampler, Kevin, Amirghodsi, Sohrab, Shechtman, Eli, Lin, Zhe, Shi, Jianbo
Recently, deep models have established SOTA performance for low-resolution image inpainting, but they lack fidelity at resolutions associated with modern cameras such as 4K or more, and for large holes. We contribute an inpainting benchmark dataset o
Externí odkaz:
http://arxiv.org/abs/2208.03552
Autor:
Zhang, Lingzhi, Zhou, Yuqian, Barnes, Connelly, Amirghodsi, Sohrab, Lin, Zhe, Shechtman, Eli, Shi, Jianbo
Image inpainting is an essential task for multiple practical applications like object removal and image editing. Deep GAN-based models greatly improve the inpainting performance in structures and textures within the hole, but might also generate unex
Externí odkaz:
http://arxiv.org/abs/2208.03357
Optical flow computation is essential in the early stages of the video processing pipeline. This paper focuses on a less explored problem in this area, the 360$^\circ$ optical flow estimation using deep neural networks to support increasingly popular
Externí odkaz:
http://arxiv.org/abs/2208.00776
Autor:
Zheng, Haitian, Lin, Zhe, Lu, Jingwan, Cohen, Scott, Shechtman, Eli, Barnes, Connelly, Zhang, Jianming, Xu, Ning, Amirghodsi, Sohrab, Luo, Jiebo
Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images. This is partially due to the lack of effective network structures that can capture bot
Externí odkaz:
http://arxiv.org/abs/2203.11947
Autor:
Zhao, Yunhan, Barnes, Connelly, Zhou, Yuqian, Shechtman, Eli, Amirghodsi, Sohrab, Fowlkes, Charless
Reference-guided image inpainting restores image pixels by leveraging the content from another single reference image. The primary challenge is how to precisely place the pixels from the reference image into the hole region. Therefore, understanding
Externí odkaz:
http://arxiv.org/abs/2201.08131