no code implementations • 23 Jun 2016 • Hossein Talebi, Peyman Milanfar
A novel, fast and practical way of enhancing images is introduced in this paper.
12 code implementations • 15 Sep 2017 • Hossein Talebi, Peyman Milanfar
Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media.
Ranked #4 on Aesthetics Quality Assessment on AVA
no code implementations • 7 Dec 2017 • Hossein Talebi, Peyman Milanfar
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images.
no code implementations • 1 Feb 2020 • Hossein Talebi, Damien Kelly, Xiyang Luo, Ignacio Garcia Dorado, Feng Yang, Peyman Milanfar, Michael Elad
In this work we aim to break the unholy connection between bit-rate and image quality, and propose a way to circumvent compression artifacts by pre-editing the incoming image and modifying its content to fit the given bits.
no code implementations • 26 Feb 2020 • Xiang Zhu, Hossein Talebi, Xinwei Shi, Feng Yang, Peyman Milanfar
We propose a realistic training data generation model for commercial satellite imagery products, which includes not only the imaging process on satellites but also the post-process on the ground.
no code implementations • 3 Aug 2020 • Xiyang Luo, Hossein Talebi, Feng Yang, Michael Elad, Peyman Milanfar
As a case study, we focus on the design of the quantization tables in the JPEG compression standard.
no code implementations • 21 Nov 2020 • Hossein Talebi, Ehsan Amid, Peyman Milanfar, Manfred K. Warmuth
Training a model on these pairwise preferences is a common deep learning approach.
2 code implementations • 16 Dec 2020 • Mauricio Delbracio, Hossein Talebi, Peyman Milanfar
More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art on reference-based perceptual losses.
no code implementations • 1 Mar 2021 • Juan Carlos Mier, Eddie Huang, Hossein Talebi, Feng Yang, Peyman Milanfar
In this paper we propose the largest image compression quality dataset to date with human perceptual preferences, enabling the use of deep learning, and we develop a full reference perceptual quality assessment metric for lossy image compression that outperforms the existing state-of-the-art methods.
4 code implementations • ICCV 2021 • Hossein Talebi, Peyman Milanfar
Moreover, we show that the proposed resizer can also be useful for fine-tuning the classification baselines for other vision tasks.
no code implementations • 3 Apr 2021 • Negin Majidi, Ehsan Amid, Hossein Talebi, Manfred K. Warmuth
Many learning tasks in machine learning can be viewed as taking a gradient step towards minimizing the average loss of a batch of examples in each training iteration.
no code implementations • CVPR 2021 • Yilin Wang, Junjie Ke, Hossein Talebi, Joong Gon Yim, Neil Birkbeck, Balu Adsumilli, Peyman Milanfar, Feng Yang
Besides the subjective ratings and content labels of the dataset, we also propose a DNN-based framework to thoroughly analyze importance of content, technical quality, and compression level in perceptual quality.
no code implementations • CVPR 2022 • Jay Whang, Mauricio Delbracio, Hossein Talebi, Chitwan Saharia, Alexandros G. Dimakis, Peyman Milanfar
Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input.
1 code implementation • CVPR 2022 • Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li
In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks.
Ranked #1 on Deblurring on HIDE (trained on GOPRO)
14 code implementations • 4 Apr 2022 • Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li
We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module.
Ranked #1 on Object Detection on COCO 2017
no code implementations • 12 Sep 2022 • Giannis Daras, Mauricio Delbracio, Hossein Talebi, Alexandros G. Dimakis, Peyman Milanfar
To reverse these general diffusions, we propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process and yields state of the art results for CelebA.
Ranked #7 on Image Generation on CelebA 64x64
no code implementations • ICCV 2023 • Mengwei Ren, Mauricio Delbracio, Hossein Talebi, Guido Gerig, Peyman Milanfar
We evaluate a single-dataset trained model on diverse datasets and demonstrate more robust deblurring results with fewer artifacts on unseen data.
1 code implementation • ICCV 2023 • Zhengzhong Tu, Peyman Milanfar, Hossein Talebi
Specifically, we select a state-of-the-art vision Transformer, MaxViT, as the baseline, and show that, if trained with MULLER, MaxViT gains up to 0. 6% top-1 accuracy, and meanwhile enjoys 36% inference cost saving to achieve similar top-1 accuracy on ImageNet-1k, as compared to the standard training scheme.
1 code implementation • 2 Oct 2023 • Kangfu Mei, Mauricio Delbracio, Hossein Talebi, Zhengzhong Tu, Vishal M. Patel, Peyman Milanfar
Our conditional-task learning and distillation approach outperforms previous distillation methods, achieving a new state-of-the-art in producing high-quality images with very few steps (e. g., 1-4) across multiple tasks, including super-resolution, text-guided image editing, and depth-to-image generation.
no code implementations • 18 Dec 2023 • Chenyang Qi, Zhengzhong Tu, Keren Ye, Mauricio Delbracio, Peyman Milanfar, Qifeng Chen, Hossein Talebi
Text-driven diffusion models have become increasingly popular for various image editing tasks, including inpainting, stylization, and object replacement.
no code implementations • 1 Apr 2024 • Kangfu Mei, Zhengzhong Tu, Mauricio Delbracio, Hossein Talebi, Vishal M. Patel, Peyman Milanfar
We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency.