Search Results for author: Peyman Milanfar

Found 53 papers, 20 papers with code

A Restoration Network as an Implicit Prior

no code implementations2 Oct 2023 Yuyang Hu, Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov

Image denoisers have been shown to be powerful priors for solving inverse problems in imaging.

Image Restoration Super-Resolution

Conditional Diffusion Distillation

no code implementations2 Oct 2023 Kangfu Mei, Mauricio Delbracio, Hossein Talebi, Zhengzhong Tu, Vishal M. Patel, Peyman Milanfar

Generative diffusion models provide strong priors for text-to-image generation and thereby serve as a foundation for conditional generation tasks such as image editing, restoration, and super-resolution.


Prompt-tuning latent diffusion models for inverse problems

no code implementations2 Oct 2023 Hyungjin Chung, Jong Chul Ye, Peyman Milanfar, Mauricio Delbracio

We propose a new method for solving imaging inverse problems using text-to-image latent diffusion models as general priors.

Deblurring Super-Resolution

MULLER: Multilayer Laplacian Resizer for Vision

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.

Image Classification Image Quality Assessment +2

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

1 code implementation CVPR 2023 Junjie Ke, Keren Ye, Jiahui Yu, Yonghui Wu, Peyman Milanfar, Feng Yang

Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset, and it has powerful zero-shot capability for aesthetic tasks such as zero-shot style classification and zero-shot IAA, surpassing many supervised baselines.

Language Modelling

Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration

no code implementations20 Mar 2023 Mauricio Delbracio, Peyman Milanfar

In conditional denoising diffusion image restoration the denoising network generates the restored image by repeatedly denoising an initial image of pure noise, conditioned on the degraded input.

Deblurring Denoising +3

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

no code implementations ICCV 2023 Ligong Han, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, Feng Yang

Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.

Data Augmentation Text-based Image Editing

MRET: Multi-resolution Transformer for Video Quality Assessment

no code implementations13 Mar 2023 Junjie Ke, Tianhao Zhang, Yilin Wang, Peyman Milanfar, Feng Yang

No-reference video quality assessment (NR-VQA) for user generated content (UGC) is crucial for understanding and improving visual experience.

Video Quality Assessment Video Recognition +1

Multiscale Structure Guided Diffusion for Image Deblurring

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.

Deblurring Denoising +2

Soft Diffusion: Score Matching for General Corruptions

no code implementations12 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.

Denoising Image Generation

MaxViT: Multi-Axis Vision Transformer

12 code implementations4 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.

Image Classification object-detection +1

MAXIM: Multi-Axis MLP for Image Processing

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 RealBlur-J (using extra training data)

Deblurring Image Deblurring +6

Deblurring via Stochastic Refinement

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.

Deblurring Image Deblurring

Solving Image PDEs with a Shallow Network

no code implementations15 Oct 2021 Pascal Tom Getreuer, Peyman Milanfar, Xiyang Luo

Partial differential equations (PDEs) are typically used as models of physical processes but are also of great interest in PDE-based image processing.

Rich Features for Perceptual Quality Assessment of UGC Videos

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.

Video Quality Assessment

COMISR: Compression-Informed Video Super-Resolution

2 code implementations ICCV 2021 Yinxiao Li, Pengchong Jin, Feng Yang, Ce Liu, Ming-Hsuan Yang, Peyman Milanfar

Most video super-resolution methods focus on restoring high-resolution video frames from low-resolution videos without taking into account compression.

Video Super-Resolution

Learning to Resize Images for Computer Vision Tasks

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.

Image Quality Assessment

High Perceptual Quality Image Denoising with a Posterior Sampling CGAN

1 code implementation6 Mar 2021 Guy Ohayon, Theo Adrai, Gregory Vaksman, Michael Elad, Peyman Milanfar

We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.

Image Denoising Vocal Bursts Intensity Prediction

Deep Perceptual Image Quality Assessment for Compression

no code implementations1 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.

Image Compression Image Quality Assessment +1

Mobile Computational Photography: A Tour

no code implementations17 Feb 2021 Mauricio Delbracio, Damien Kelly, Michael S. Brown, Peyman Milanfar

The first mobile camera phone was sold only 20 years ago, when taking pictures with one's phone was an oddity, and sharing pictures online was unheard of.


Polyblur: Removing mild blur by polynomial reblurring

no code implementations16 Dec 2020 Mauricio Delbracio, Ignacio Garcia-Dorado, Sungjoon Choi, Damien Kelly, Peyman Milanfar

The proposed method estimates and removes mild blur from a 12MP image on a modern mobile phone in a fraction of a second.

Deblurring Super-Resolution

Projected Distribution Loss for Image Enhancement

2 code implementations16 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.

Deblurring Demosaicking +5

Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data

1 code implementation ICCV 2021 Abdullah Abuolaim, Mauricio Delbracio, Damien Kelly, Michael S. Brown, Peyman Milanfar

Leveraging these realistic synthetic DP images, we introduce a recurrent convolutional network (RCN) architecture that improves deblurring results and is suitable for use with single-frame and multi-frame data (e. g., video) captured by DP sensors.

Ranked #12 on Image Defocus Deblurring on DPD (Dual-view) (using extra training data)

Deblurring Image Defocus Deblurring

Multi-path Neural Networks for On-device Multi-domain Visual Classification

no code implementations10 Oct 2020 Qifei Wang, Junjie Ke, Joshua Greaves, Grace Chu, Gabriel Bender, Luciano Sbaiz, Alec Go, Andrew Howard, Feng Yang, Ming-Hsuan Yang, Jeff Gilbert, Peyman Milanfar

This approach effectively reduces the total number of parameters and FLOPS, encouraging positive knowledge transfer while mitigating negative interference across domains.

General Classification Neural Architecture Search +1

The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study

no code implementations3 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.


Regularization by Denoising via Fixed-Point Projection (RED-PRO)

no code implementations1 Aug 2020 Regev Cohen, Michael Elad, Peyman Milanfar

Two such methods are the Plug-and-Play Prior (PnP) and Regularization by Denoising (RED).

Deblurring Denoising +2

GIFnets: Differentiable GIF Encoding Framework

no code implementations CVPR 2020 Innfarn Yoo, Xiyang Luo, Yilin Wang, Feng Yang, Peyman Milanfar

DitherNet manipulates the input image to reduce color banding artifacts and provides an alternative to traditional dithering.

Creating High Resolution Images with a Latent Adversarial Generator

1 code implementation4 Mar 2020 David Berthelot, Peyman Milanfar, Ian Goodfellow

That is to say, instead of generating an arbitrary image as a sample from the manifold of natural images, we propose to sample images from a particular "subspace" of natural images, directed by a low-resolution image from the same subspace.

Image Super-Resolution Vocal Bursts Intensity Prediction

Super-Resolving Commercial Satellite Imagery Using Realistic Training Data

no code implementations26 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.

satellite image super-resolution

Image Stylization: From Predefined to Personalized

no code implementations22 Feb 2020 Ignacio Garcia-Dorado, Pascal Getreuer, Bartlomiej Wronski, Peyman Milanfar

We present a framework for interactive design of new image stylizations using a wide range of predefined filter blocks.

Image Stylization

Better Compression with Deep Pre-Editing

no code implementations1 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.

Distortion Agnostic Deep Watermarking

no code implementations CVPR 2020 Xiyang Luo, Ruohan Zhan, Huiwen Chang, Feng Yang, Peyman Milanfar

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image.

LIDIA: Lightweight Learned Image Denoising with Instance Adaptation

1 code implementation17 Nov 2019 Gregory Vaksman, Michael Elad, Peyman Milanfar

This work proposes a novel lightweight learnable architecture for image denoising, and presents a combination of supervised and unsupervised training of it, the first aiming for a universal denoiser and the second for adapting it to the incoming image.

Grayscale Image Denoising Image Denoising

Deep K-SVD Denoising

no code implementations28 Sep 2019 Meyer Scetbon, Michael Elad, Peyman Milanfar

The question we address in this paper is whether K-SVD was brought to its peak in its original conception, or whether it can be made competitive again.


Handheld Multi-Frame Super-Resolution

3 code implementations8 May 2019 Bartlomiej Wronski, Ignacio Garcia-Dorado, Manfred Ernst, Damien Kelly, Michael Krainin, Chia-Kai Liang, Marc Levoy, Peyman Milanfar

In this paper, we supplant the use of traditional demosaicing in single-frame and burst photography pipelines with a multiframe super-resolution algorithm that creates a complete RGB image directly from a burst of CFA raw images.

Demosaicking Multi-Frame Super-Resolution

DeepRED: Deep Image Prior Powered by RED

1 code implementation25 Mar 2019 Gary Mataev, Michael Elad, Peyman Milanfar

Inverse problems in imaging are extensively studied, with a variety of strategies, tools, and theory that have been accumulated over the years.

Deblurring Denoising +1

Rendition: Reclaiming what a black box takes away

no code implementations23 Apr 2018 Peyman Milanfar

The premise of our work is deceptively familiar: A black box $f(\cdot)$ has altered an image $\mathbf{x} \rightarrow f(\mathbf{x})$.

Local Kernels that Approximate Bayesian Regularization and Proximal Operators

no code implementations9 Mar 2018 Frank Ong, Peyman Milanfar, Pascal Getreuer

In this work, we broadly connect kernel-based filtering (e. g. approaches such as the bilateral filters and nonlocal means, but also many more) with general variational formulations of Bayesian regularized least squares, and the related concept of proximal operators.


Graphic Narrative with Interactive Stylization Design

no code implementations18 Dec 2017 Ignacio Garcia-Dorado, Pascal Getreuer, Madison Le, Robin Debreuil, Alex Kauffmann, Peyman Milanfar

In parallel to this manual design, we propose a novel procedural approach that automatically assembles sequences of filters for innovative results.


Learned Perceptual Image Enhancement

no code implementations7 Dec 2017 Hossein Talebi, Peyman Milanfar

Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images.

Image Enhancement Tone Mapping

BLADE: Filter Learning for General Purpose Computational Photography

no code implementations29 Nov 2017 Pascal Getreuer, Ignacio Garcia-Dorado, John Isidoro, Sungjoon Choi, Frank Ong, Peyman Milanfar

The Rapid and Accurate Image Super Resolution (RAISR) method of Romano, Isidoro, and Milanfar is a computationally efficient image upscaling method using a trained set of filters.

Demosaicking Denoising +1

NIMA: Neural Image Assessment

8 code implementations15 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.

Aesthetics Quality Assessment Video Quality Assessment

The Little Engine that Could: Regularization by Denoising (RED)

2 code implementations9 Nov 2016 Yaniv Romano, Michael Elad, Peyman Milanfar

As opposed to the $P^3$ method, we offer Regularization by Denoising (RED): using the denoising engine in defining the regularization of the inverse problem.

Deblurring Image Deblurring +3

Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Images

1 code implementation26 Sep 2016 Sujoy Kumar Biswas, Peyman Milanfar

Pedestrian detection in thermal infrared images poses unique challenges because of the low resolution and noisy nature of the image.

Pedestrian Detection

Style-Transfer via Texture-Synthesis

2 code implementations10 Sep 2016 Michael Elad, Peyman Milanfar

Recent work on this problem adopting Convolutional Neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained.

Style Transfer Texture Synthesis

Fast Multi-Layer Laplacian Enhancement

no code implementations23 Jun 2016 Hossein Talebi, Peyman Milanfar

A novel, fast and practical way of enhancing images is introduced in this paper.

Denoising image smoothing

RAISR: Rapid and Accurate Image Super Resolution

no code implementations3 Jun 2016 Yaniv Romano, John Isidoro, Peyman Milanfar

Our approach additionally includes an extremely efficient way to produce an image that is significantly sharper than the input blurry one, without introducing artifacts such as halos and noise amplification.

Image Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.