Marcos V. Conde

I'm a PhD Researcher in Artificial Intelligence at the University of Würzburg, advised by Prof. Radu Timofte. My work is supported by Sony PlayStation (FTG) where I'm a Computer Vision Research Scientist.
I am also Senior Data Scientist (Kaggle Grandmaster) at H2O.ai.

From 2020 to 2022, I worked at Huawei Noah’s Ark Lab (London) supervised by Dr. Eduardo Pérez-Pellitero and Prof. Aleš Leonardis, and received the best intern award for my work on neural camera ISPs.

M.Sc. in Computer Vision from the Autonomous University of Barcelona (UAB) with honours for my work on Real-time Photography Enhancement.

Email  /  Google Scholar  /  GitHub  /  Kaggle  /  Hugging Face 🤗


井の中の蛙大海を知らず  |  井鼃不可以語於海者,拘於虛也
"I learned very early the difference between knowing the name of something and knowing something." - Richard Feynmann

profile photo

News

[June 2024] I co-organize the Advances in Image Manipulation (AIM) Workshop at ECCV 2024. Call for papers open!

[June 2024] ECCV 2024 (Oral) InstructIR: High-Quality Image Restoration Following Human Instructions is trending on HF 🤗. Read the preprint | Watch the demo Video | Our demo is available Try it now! (click)

[June 2024] We organize the 1st AI for Streaming Workshop at CVPR 2024. Check the awesome speakers and challenges in the website. The workshop is sponsored by Sony PlayStation, Meta and Netflix.

[Jan 2024] I co-organize the New Trends in Image Restoration and Enhancement (NTIRE) Workshop at CVPR 2024.
I organize the RAW SR and Portrait IQA Challenges.

Research

My current research interests include neural networks, deep learning, low-level computer vision, inverse problems, computational photography and photorealism. How can we improve/change/enhance cameras and vision using AI?
Representative papers are highlighted.

(Past/Present) Collaborators: Radu Timofte  /  Michael S. Brown (York University, Samsung)  /  Tom E. Bishop (Glass Imaging)  /  Javier Vazquez-Corral (CVC, UAB)  /  Sira Ferradans (DXOMARK)  /  Ioannis Katsavounidis (Meta, AOMedia)

InstructIR: High-Quality Image Restoration Following Human Instructions
Marcos V. Conde, Gregor Geigle, Radu Timofte
ECCV, 2024
project page / GitHub / arXiv / Video / Twitter X / Demo 🤗

InstructIR takes as input a degraded image and a human-written instruction for how to improve that image. The (single) neural model performs all-in-one image restoration. We achieve state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement.

Simple Image Signal Processing using Global Context Guidance
Omar Elezabi, Marcos V. Conde, Radu Timofte
ICIP, 2024
arXiv / GitHub

First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Second, we propose an efficient and simple neural ISP that utilizes our proposed module.

NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement
Marcos V. Conde, Javier Vazquez-Corral , Michael S. Brown, Radu Timofte
AAAI, 2024   (23.75% Acceptance rate)
project page / arXiv / GitHub & Demo / Video

NILUTs are neural representations of real 3D LUTs for controllable photo-realistic image enhancement and color manipulation. Moreover, a NILUT can be extended to incorporate multiple styles into a single network with the ability to blend styles implicitly.

Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey
Marcos V. Conde, Zhijun Lei, Wen Li, Cosmin Stejerean, Ioannis Katsavounidis, Radu Timofte
CVPR Workshop, 2024
arXiv / GitHub

Collaboration with Meta. This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. The images are compressed using the modern AVIF codec, instead of JPEG.

Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey
Nicolas Chahine, Marcos V. Conde, Daniela Carfora, Gabriel Pacianotto, Benoit Pochon, Sira Ferradans, Radu Timofte
CVPR Workshop, 2024
arXiv / GitHub

Collaboration with DXOMARK. This paper reviews the NTIRE 2024 Portrait Quality Assessment Challenge, highlighting the proposed solutions and results. This challenge aims to obtain an efficient deep neural network capable of estimating the perceptual quality of real portrait photos.

Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
Marcos V. Conde, Florin Vasluianu, Radu Timofte
CVPR Workshop, 2024
arXiv / GitHub

New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur.

BSRAW: Improving Blind RAW Image Super-Resolution
Marcos V. Conde, Florin Vasluianu, Radu Timofte
WACV, 2024
arXiv / cvf Proceedings / GitHub

We advance RAW sensor images up-scaling (Super-Resolution). We explore diverse image degradations (e.g. Noise, Blur) to emulate a low-resolution RAW image, and we train a neural network to upsample it.

Efficient multi-lens bokeh effect rendering and transformation
Tim Seizinger*, Marcos V. Conde*, Manuel Kolmet, Tom E Bishop, Radu Timofte
CVPR Workshop, 2023
paper / cvf Proceedings / GitHub

EBokehNet, an efficient state-of-the-art solution for Bokeh effect transformation and rendering. We can render Bokeh from all-in-focus images, or transform the Bokeh of one lens to the effect of another lens without harming the sharp foreground in the image.

Towards Real-Time 4K Image Super-Resolution
Eduard Zamfir, Marcos V. Conde, Radu Timofte
CVPR Workshop, 2023
paper / cvf Proceedings / GitHub

The paper presents an exhaustive study of baseline methods for real-time image SR. The methods allow 60 FPS and even 120 FPS.

Efficient Deep Models for Real-Time 4K Image Super-Resolution. NTIRE 2023 Benchmark and Report
Marcos V. Conde, Eduard Zamfir, Radu Timofte
CVPR Workshop, 2023
paper / cvf Proceedings / GitHub

The paper gauges the state-of-the-art methods for real-time 4K upscaling using our new dataset and benchmark protocol. Ovr 100 participants joined the challenge and 15 teams proposed diverse solutions. The methods allow 60 FPS and even 120 FPS on regular GPUs.

Perceptual Image Enhancement for Smartphone Real-Time Applications
Marcos V. Conde, Florin Vasluianu, Javier Vazquez-Corral, Radu Timofte
WACV, 2023   (Oral Presentation, Spotlight)
arXiv / cvf Proceedings / GitHub

We propose LPIENet, a lightweight network for perceptual image enhancement, with the focus on deploying it on smartphones. The model was tested for image denoising, deblurring, and HDR correction.

Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte
ECCV Workshop , 2022
arXiv / eccv Proceedings / GitHub / Demo (3M runs!)

Super-resolution of compressed images using transformers. We use the Swin Transformer V2, to improve SwinIR for image super-resolution, and in particular, the compressed input scenario. Using this method we can tackle the major issues in training transformer vision models, such as training instability, resolution gaps between pre-training and fine-tuning.

Reversed Image Signal Processing and RAW Reconstruction
Marcos V. Conde, Radu Timofte, et al.
ECCV Workshop , 2022
arXiv / eccv Proceedings / GitHub

This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation.

Model-Based Image Signal Processors via Learnable Dictionaries
Marcos V. Conde, Steven McDonagh, Matteo Maggioni , Aleš Leonardis, Eduardo Pérez-Pellitero
AAAI, 2022   (Oral Presentation, Spotlight)
project page / GitHub / arXiv / Poster

Hybrid model-based and data-driven approach for modelling ISPs using learnable dictionaries. We explore RAW image reconstruction and improve downstream tasks like RAW Image Denoising via raw data augmentation-synthesis.

CLIP-Art: Contrastive Pre-Training for Fine-Grained Art Classification
Marcos V. Conde, Kerem Turgutlu
CVPR Workshop, 2021
arXiv / cvpr Proceedings / GitHub / Kaggle

We were one of the 1st attempts to use CLIP (Contrastive Language-Image Pre-Training) for training a neural network on a variety of art images and descriptions, being able to learn directly from raw descriptions about images, or if available, curated labels.

Academic Service

Teaching: Image Processing and Computational Photography (IPCP), Computer Vision

Reviewer: CVPR 2022-2024, ECCV 2022/24, ICCV 2023, AAAI 2023/24, SIGGRAPH 2024, ACCV 2024, IEEE Transactions on Image Processing, IEEE Transactions on Computational Imaging

Workshops: AIM 2024 ECCV  /  AI for Streaming (AIS 2024) CVPR  /  NTIRE 2024 CVPR  /  VQEG 2023  /  NTIRE 2023 CVPR  /  AIM 2022 ECCV

Other Projects

H2O Open Ecosystem for LLMs

We introduce a complete open-source ecosystem for developing and testing LLMs. The goal of this project is to boost open alterna- tives to closed-source approaches.
Authors: Arno Candel, Jon McKinney, Philipp Singer, Pascal Pfeiffer, Maximilian Jeblick, Chun Ming Lee, Marcos V. Conde

ACL EMNLP Proceedings  /  Demo  /  GitHub
Motion Prediction for Autonomous Driving

We proposed multiple methods for motion prediction in Autonomous Driving. The methods were presented at CVPR Workshops, ICRA, and IEEE Transactions on Intelligent Transportation Systems (T-ITS, Q1, IF:8.5).
Authors: Carlos Gómez-Huélamo, Marcos V. Conde

IEEE Journal  /  CVPRW  /  GitHub
Event-Based Eye Tracking - AIS Challenge CVPR 2024

This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge. The task of the challenge focuses on processing eye movement recorded with event cameras and predicting the pupil center of the eye.
Authors: Zuowen Wang, Chang Gao, Zongwei Wu, Marcos V. Conde, Radu Timofte, Shih-Chii Liu, Qinyu Chen

arXiv  /  Kaggle  /  GitHub  /  Project
Kuzushiji Recognition (Nov. 2019)

I was invited by Japan’s National Institute of Informatics (NII) and ROIS-DS Center for Open Data in the Humanities (CODH) to present a novel solution for the Kuzushiji Recognition Challenge at the Japanese Culture and AI Symposium 2019 in Tokyo.
Organizers: Dr. Asanobu Kitamoto, Tarin Clanuwat, Alex Lamb.

GitHub  /  NHK News Report  /  Awards Ceremony Video


Design and source code from Jon Barron's website.