NTIRE: 11th New Trends in Image Restoration and Enhancement workshop and challenges 2026
In conjunction with CVPR 2026

https://www.cvlai.net/ntire/2026/
Contact: radu.timofte [at] uni-wuerzburg.de

Scope

Image restoration, enhancement and manipulation are key computer vision tasks, aiming at the restoration of degraded image content, the filling in of missing information, or the needed transformation and/or manipulation to achieve a desired target (with respect to perceptual quality, contents, or performance of apps working on such images). Recent years have witnessed an increased interest from the vision and graphics communities in these fundamental topics of research. Not only has there been a constantly growing flow of related papers, but also substantial progress has been achieved.

Each step forward eases the use of images by people or computers for the fulfillment of further tasks, as image restoration, enhancement and manipulation serves as an important frontend. Not surprisingly then, there is an ever growing range of applications in fields such as surveillance, the automotive industry, electronics, remote sensing, or medical image analysis etc. The emergence and ubiquitous use of mobile and wearable devices offer another fertile ground for additional applications and faster methods.

This workshop aims to provide an overview of the new trends and advances in those areas. Moreover, it will offer an opportunity for academic and industrial attendees to interact and explore collaborations.

This workshop builds upon the success of the previous NTIRE editions: at CVPR 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024, and 2025 and at ACCV 2016. Moreover, it relies on all the people associated with the CLIC 2018, 2019, 2020, 2021, 2022, 2024, PIRM 2018, AIGENS 2024 and 2025, AIM 2019, 2020, 2021, 2022, 2024, 2025, MAI 2021, 2022, 2023, 2024, and 2025 events such as organizers, PC members, distinguished speakers, authors of published paper, challenge participants and winning teams.


Topics

Papers addressing topics related to image restoration, enhancement and manipulation are invited. The topics include, but are not limited to:


● Image/video inpainting
● Image/video deblurring
● Image/video denoising
● Image/video upsampling and super-resolution
● Image/video filtering
● Image/video de-hazing, de-raining, de-snowing, etc.
● Demosaicing
● Image/video compression
● Removal of artifacts, shadows, glare and reflections, etc.
● Image/video enhancement: brightening, color adjustment, sharpening, etc.
● Style transfer
● Hyperspectral image restoration, enhancement, manipulation
● Underwater image restoration, enhancement, manipulation
● Light field image restoration, enhancement, manipulation
● Methods robust to changing weather conditions / adverse outdoor conditions
● Image/video restoration, enhancement, manipulation on constrained settings/mobile devices
● Visual domain translation
● Multimodal translation
● Perceptual enhancement
● Perceptual manipulation
● Depth estimation
● Image/video generation and hallucination
● Image/video quality assessment
● Image/video semantic segmentation
● Saliency and gaze estimation
● Studies and applications of the above.


Submission


A paper submission has to be in English, in pdf format, and at most 8 pages (excluding references) in CVPR style.
https://cvpr.thecvf.com/Conferences/2026/AuthorGuidelines
Author Kit: https://github.com/cvpr-org/author-kit/archive/refs/tags/CVPR2026-v1(latex).zip
Submission site: https://cmt3.research.microsoft.com/NTIRE2026
The review process is double blind.

Accepted and presented papers will be published after the conference in the CVPR Workshops Proceedings on by IEEE (http://www.ieee.org) and Computer Vision Foundation (https://openaccess.thecvf.com/menu).


Workshop Dates

● Regular Papers submission deadline: March 10, 2026
● Challenge Papers submission deadline: March 24, 2026
● Papers reviewed elsewhere submission deadline: March 24, 2026
● Decisions: March 31, 2026
● Camera Ready Deadline: April 10, 2026



NTIRE 2026 has the following associated challenges:

● Ambient Light Normalization - Track White Lighting
● Ambient Light Normalization - Track Color Lighting
● Rip Current Detection and Segmentation
● HR Depth from Images of Specular and Transparent Surfaces - Track Stereo
● HR Depth from Images of Specular and Transparent Surfaces - Track Metric Mono
● Day and Night Raindrop Removal for Dual-Focused Images
● Learned Smartphone ISP with Unpaired Data
● NightTime Image Dehazing
● Reflection Removal in the Wild
● Image Shadow Removal
● Bitstream-corrupted Video Restoration
● Efficient Burst HDR and Restoration
● Robust AI-Generated Image Detection in the Wild
● 3D Content Super-Resolution - Track 1 Bicubic Degradation
● 3D Content Super-Resolution - Track 2 Realistic Degradation
● Light Field Image Super-Resolution - Track 1 Classic
● Light Field Image Super-Resolution - Track 2 Efficiency
● Light Field Image Super-Resolution - Track 3 Large Model
● Low Light Image Enhancement
● Joint Denoising and Low Light Image Enhancement
● Image Denoising
● Event-Based Image Deblurring
● Blind Computational Aberration Correction
● Robust Deepfake Detection
● Photography Retouching Transfer
● Controllable Aperture Bokeh Rendering
● Video Saliency Prediction
● Restore Any Image Model (RAIM) - Track 1: Professional Image Quality Assessment
● Restore Any Image Model (RAIM) - Track 2: Multi-Exposure Image Fusion in Dynamic Scenes
● Restore Any Image Model (RAIM) - Track 3: AI Flash Portrait
● High FPS Video Frame Interpolation - Track 1 Classic
● High FPS Video Frame Interpolation - Track 2 Extreme
● Cross-Domain Few-Shot Object Detection
● X-AIGC Quality Assessment - Track 1: Text-to-3D
● X-AIGC Quality Assessment - Track 2: Image Editing
● Short-form UGC Video Restoration in the Wild with Generative Models
● Image Super-Resolution (x4)
● Mobile Real-World Image Super-Resolution
● Remote Sensing Infrared Image Super-Resolution
● Real-World Face Restoration
● Efficient Low-Light Image Enhancement
● End-to-End Financial Table Reconstruction and Reasoning from Degraded Images
● Low-light Enhancement: Twilight Cowboy
● Efficient Super-Resolution
● Efficient Real-World Deblurring
● 3D Restoration and Reconstruction



PARTICIPATION

To learn more about the challenges and to participate:
https://www.cvlai.net/ntire/2026/


Challenges Dates

● Release of train data: January 15?, 2026
● Validation server online: January 30?, 2026
● Competitions end: March 17, 2026


Contact

Email: radu.timofte [at] uni-wuerzburg.de
Website: https://www.cvlai.net/ntire/2026/