datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
NTIRE-RobustAIGenDetection-train
Training set for NTIRE 2026 Robust AI-Generated Image Detection in the Wild
Robust AI-Generated Image Detection in the Wild Challenge is organized as a part of the New Trends in Image Restoration and Enhancement Workshop in conjunction with CVPR 2026.
Challenge overview
Text-to-image (T2I) models have made synthetic images nearly indistinguishable from real photos in many cases, which creates serious challenges for trust, authenticity, forensics, and content… See the full description on the dataset page: https://huggingface.co/datasets/deepfakesMSU/NTIRE-RobustAIGenDetection-train.NTIRE22_InpaintingNTIRE-Haze
NTIRE-Haze: Real Haze-Machine Dehazing Benchmarks (Unofficial Composite Mirror)
Unofficial composite redistribution of the four NTIRE real-haze dehazing benchmarks, I-Haze, O-Haze, Dense-Haze, and NH-Haze (Ancuti et al., 2018-2020), packaged for direct use with ClearView's dataset pipeline. This is ClearView's first dehazing dataset, a degradation category distinct from rain streaks, raindrops, or snow.
Disclaimer
This repository is not an official… See the full description on the dataset page: https://huggingface.co/datasets/dronefreak/NTIRE-Haze.NTIRE-RobustAIGenDetection-val
Validation set for NTIRE 2026 Robust AI-Generated Image Detection in the Wild (updated)
Note: This is an updated version of the dataset. For challenge submissions, please make sure you use this version.
Robust AI-Generated Image Detection in the Wild Challenge is organized as a part of the New Trends in Image Restoration and Enhancement Workshop in conjunction with CVPR 2026.
Challenge overview
Text-to-image (T2I) models have made synthetic images nearly… See the full description on the dataset page: https://huggingface.co/datasets/deepfakesMSU/NTIRE-RobustAIGenDetection-val.ntire-robustaigendetection-fakentire-robustaigendetection-realNTIRE-RobustAIGenDetection-test-public
Test set for NTIRE 2026 Robust AI-Generated Image Detection in the Wild
Robust AI-Generated Image Detection in the Wild Challenge is organized as a part of the New Trends in Image Restoration and Enhancement Workshop in conjunction with CVPR 2026.
Challenge overview
Text-to-image (T2I) models have made synthetic images nearly indistinguishable from real photos in many cases, which creates serious challenges for trust, authenticity, forensics, and content safety. At… See the full description on the dataset page: https://huggingface.co/datasets/deepfakesMSU/NTIRE-RobustAIGenDetection-test-public.THQA-NTIRE🚀 CVPR NTIRE 2025 - XGC Quality Assessment - Track 3: Talking Head (THQA-NTIRE)
"Who is a Better Talker?"
Supervisors: Xiaohong Liu1, Xiongkuo Min1, Guangtao Zhai1, Jie Guo2, Radu Timofte Student Organizers: Yingjie Zhou1, Zicheng Zhang1, Farong Wen1, Yanwei Jiang1, XiLei Zhu1, Li Xu2, Jun Jia1, Wei Sun1 Email: Yingjie Zhou (zyj2000@sjtu.edu.cn) 1Shanghai Jiao Tong University 2PengCheng Laboratory CVPR NTIRE 2025 XGC Quality Assessment - Track 3: Talking Head… See the full description on the dataset page: https://huggingface.co/datasets/zyj2000/THQA-NTIRE.3DGCQA-NTIRENTIRE_LLE_2025
NTIRE 2025 Low Light Image Enhancement Challenge Dataset
Overview
The NTIRE 2025 dataset is crafted to benchmark low-light image enhancement algorithms, featuring a diverse set of challenging low-light conditions. It is structured to support both the development and evaluation phases of the challenge.
Dataset Composition
Training Set: 219 images with paired low-light inputs and corresponding ground truth images.
Validation Set: 46 images provided as low-light… See the full description on the dataset page: https://huggingface.co/datasets/okhater/NTIRE_LLE_2025.NTIRENTIRERobustDeepfakeDetectionChallengeCVPR2026
Challenge link: https://www.codabench.org/competitions/12795/#/pages-tab
NTIRE2026_UGC_Submission_xingyananntire-patchdllNTIRE_2026_Financial_ReceiptNTIRE2026ESRResultsntireNTIRE2025_Dn50_Challenge_Team02_TestoutNTIRE_LLE_2025
NTIRE 2025 Low Light Image Enhancement Challenge Dataset
Overview
The NTIRE 2025 dataset is crafted to benchmark low-light image enhancement algorithms, featuring a diverse set of challenging low-light conditions. It is structured to support both the development and evaluation phases of the challenge.
Dataset Composition
Training Set: 219 images with paired low-light inputs and corresponding ground truth images.
Validation Set: 46 images provided… See the full description on the dataset page: https://huggingface.co/datasets/Bubu0320/NTIRE_LLE_2025.NTIRE2025_RealWorld_Face_Restoration_team14_DSS_test_resultntire-webdatasetntire2026-result