Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Mei, Kangfu"'
Autor:
Mei, Kangfu, Tu, Zhengzhong, Delbracio, Mauricio, Talebi, Hossein, Patel, Vishal M., Milanfar, Peyman
We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion models, the
Externí odkaz:
http://arxiv.org/abs/2404.01367
Recovering textures under shadows has remained a challenging problem due to the difficulty of inferring shadow-free scenes from shadow images. In this paper, we propose the use of diffusion models as they offer a promising approach to gradually refin
Externí odkaz:
http://arxiv.org/abs/2312.02156
Autor:
Mei, Kangfu, Delbracio, Mauricio, Talebi, Hossein, Tu, Zhengzhong, Patel, Vishal M., Milanfar, Peyman
Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption is hinder
Externí odkaz:
http://arxiv.org/abs/2310.01407
Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. While DPF shows great potential for unifying data generation of various modalities including images, videos, and 3D geometry, it does not
Externí odkaz:
http://arxiv.org/abs/2305.14674
Conditional diffusion probabilistic models can model the distribution of natural images and can generate diverse and realistic samples based on given conditions. However, oftentimes their results can be unrealistic with observable color shifts and te
Externí odkaz:
http://arxiv.org/abs/2212.07352
Autor:
Mei, Kangfu, Patel, Vishal M.
Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in an implic
Externí odkaz:
http://arxiv.org/abs/2212.00235
Although many long-range imaging systems are designed to support extended vision applications, a natural obstacle to their operation is degradation due to atmospheric turbulence. Atmospheric turbulence causes significant degradation to image quality
Externí odkaz:
http://arxiv.org/abs/2208.11284
The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains. But the optimization of end-to-end denoising learning like pixel-wise losses is performed in a sample-to-sample manner, wh
Externí odkaz:
http://arxiv.org/abs/2207.09302
Atmospheric turbulence deteriorates the quality of images captured by long-range imaging systems by introducing blur and geometric distortions to the captured scene. This leads to a drastic drop in performance when computer vision algorithms like obj
Externí odkaz:
http://arxiv.org/abs/2204.08974
In many practical applications of long-range imaging such as biometrics and surveillance, thermal imagining modalities are often used to capture images in low-light and nighttime conditions. However, such imaging systems often suffer from atmospheric
Externí odkaz:
http://arxiv.org/abs/2204.03057