HrishavBakulBarua/GTA-HDR

WACV 2025: Theory, Experiments, Dataset, and Code for our newly proposed LDR → HDR Deep Learning Dataset called GTA-HDR

35
/ 100
Emerging

This project offers a specialized dataset and tools for creators working with digital imagery, particularly in video games or simulations. It takes high dynamic range (HDR) image data from sources like Grand Theft Auto V gameplay and processes it into both HDR and standard dynamic range (SDR/LDR) formats. This helps researchers and developers create and evaluate deep learning models that can reconstruct detailed HDR images from less detailed SDR inputs.

Use this if you are developing or evaluating deep learning models for HDR image reconstruction and need a large, diverse dataset of ground truth HDR images and corresponding distorted HDR or LDR pairs.

Not ideal if you are looking for a simple tool to convert individual LDR images to HDR without involving deep learning model development or extensive dataset creation.

game-development computer-graphics image-processing visual-effects digital-media
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

31

Forks

2

Language

License

Last pushed

Nov 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HrishavBakulBarua/GTA-HDR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.