Artificial Intelligence Datasets Qualcomm Rasterized Images for Super-resolution Processing Dataset
The Qualcomm Rasterized Images for Super-resolution Processing dataset was created to facilitate the development and research of super-resolution algorithms for gaming. The dataset consists of parallel captures of various scenes in different modalities and resolutions. It is designed to be diverse, with a variety of backgrounds and models, to better generalize to new video games.
For a detailed description of the dataset characteristics and research applications, see our paper titled “Efficient Neural Supersampling on the Qualcomm Rasterized Images for Super-resolution Processing Dataset”
DATASET MODALITIES
The Qualcomm Rasterized Images for Super-resolution Processing dataset consists of sequences of computer-generated frames captured at 60 frames per second. For each frame, multiplemodalities, including color, depth and motion vectors, are rendered at different resolutions ranging from 270p to 1080p. These modalities can be generated using default parameters or mipbiased, jittered, or both mipbiased and jittered.
Example of data modalities available in the [anonymized name] dataset. (first row, from left to right): Native 270p, Negative 2 mipbiased 270p, Negative 1.58 mipbiased 360p, Negative 1 mipbiased 540p. (second row, from left to right): 540p depth, 540p motion vectors, Native 1080p, Enhanced 1080p
DATASET COMPOSITION AND COLLECTION PROCESS
The dataset consists of renders from 13 scenes in total, with 10 of them allocated for training and the remaining 3 reserved for evaluation. The table below provides a list of the scenes and the number of segments and frames available for each.
Scene compositions. Our dataset includes 3D assets sourced either from the Unity Asset Store, or from various permissively licensed open-source GitHub projects. To make the data more representative of real-world gaming scenarios, we manually added animated characters to the scene. We also occasionally add textual UI elements on top of animated characters to make the algorithms more robust to elements without associated depth or motion vector information. A list of the assets used is provided below.
COMMERCIAL BASELINES
In this dataset, we have also included images generated by commercial upscaling solutions integrated into Unity on the same frames used for evaluation. At the time of the dataset collection, these included Nvidia’s DLSS 2.2.11.0 and AMD’s FSR 1.2, which can serve as reference baselines to assess the performance of new algorithms.
POTENTIAL USE BEYOND SUPER-RESOLUTION
While this dataset was primarily created to facilitate the development of super-resolution algorithms for gaming applications; however, we believe that it could be useful for other tasks, such as optical flow estimation.
Dataset license
The Qualcomm Rasterized Images for Super-resolution Processing dataset is available for research purposes.
Dataset download
You will need to be logged in with your Qualcomm OneID account in order to download. If you do not have an active account, please click the "Register" button at the top of the page to get started.
Please download ALL files, including the download instructions.
For a detailed description of the dataset characteristics and research applications, see our paper titled “Efficient Neural Supersampling on a Novel Gaming Dataset”
Dataset Citation Instructions
@inproceedings{mercier2023supersampling,
title={Efficient Neural Supersampling on a Novel Gaming Dataset},
author={Mercier, Antoine and Erasmus, Ruan and Savani, Yashesh and Dhingra, Manik and Porikli, Fatih and
Berger, Guillaume},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision. ICCV'23.},
year={2023}
}
Qualcomm AI Research
At Qualcomm AI Research, we are advancing AI to make its core capabilities – perception, reasoning, and action – ubiquitous across devices. Our mission is to make breakthroughs in fundamental AI research and scale them across industries. By bringing together some of the best minds in the field, we’re pushing the boundaries of what’s possible and shaping the future of AI.
Qualcomm AI Research continues to invest in and support deep-learning research in computer vision. The publication of the Qualcomm Rasterized Images for Super-resolution Processing dataset for use by the AI research community is one of our many initiatives.
Find out more about Qualcomm AI Research.
For any questions or technical support, please contact us at [email protected]
Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.