Qualcomm Rasterized Images Dataset
Qualcomm Rasterized Images Dataset
chip image

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.

SceneSplitSegmentsFrames Per SegmentsTotal FramesIncludes stops
FloodedGroundsTrain2130630No
SciFifacilityTrain2130630No
Sun Temple
Train
36301080No
CB-Apocalypse
Train
30
30900No
SciFiBase
Train
41301230No
FloodedGrounds Bridges
Train20130
600Yes
SciliBase NightStartStop
Train

2030600Yes
ScitiBaseStartStop
Train

21301630Yes
Sun TempleBush
Train1130330Yes
Sun TempleLamps
Train2130630Yes
AbandonedSchool
Test21300600Yes
SpaceShipDemoTest2300600Yes
Seaport2Test13003001Yes
Total Training
 2423017260 
Total Test
 53001500 
Total --8760  
Scene Split Segments Frames Per Segments Total Frames Includes stops
FloodedGrounds Train 21 30 630 No
SciFifacility Train 21 30 630 No
Sun Temple Train 36 30 1080 No
CB-Apocalypse Train 30 30 900 No
SciFiBase Train 41 30 1230 No
FloodedGrounds Bridges Train 201 30 600 Yes
SciliBase NightStartStop Train 20 30 600 Yes
ScitiBaseStartStop Train 21 301 630 Yes
Sun TempleBush Train 11 30 330 Yes
Sun TempleLamps Train 21 30 630 Yes
AbandonedSchool Test 21 300 600 Yes
SpaceShipDemo Test 2 300 600 Yes
Seaport2 Test 1 300 3001 Yes
Total Training   242 301 7260  
Total Test   5 300 1500  
Total   - - 8760  

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.

Scene Assets Used Source
CB-Apocalypse CBU: Apocalypse Edition Unity Asset Store
ULTIMATE ANIMATION Unity Asset Store
COLLECTION
Animal Pack Deluxe Unity Asset Store
Customizable Survivors Pack Unity Asset Store
SciFifacility Sci-Fi Facility Unity Asset Store
Robot Warnors Cartoon Unity Asset Store
Flooded Grounds
FloodedGrounds Bridges
Flooded Grounds Unity Asset Store
Ghoul-zombie Unity Asset Store
Zombie Unity Asset Store
Fantastic Creature #1| Unity Asset Store
SciFiBase
ScifiBaseNightStartStop
Sciti BaseStartStop
Sci-Fi base Unity Asset Store
Robot 1| Unity Asset Store
Robot Warriors Cartoon Unity Asset Store
Robot Sphere Unity Asset Store
Sun Temple Sun Temple Unity Asset Store
Animal Pack Deluxe Unity Asset Store
Dragon for Boss Monster: HP Unity Asset Store
Sun TempkBush Sun Temple Unity Asset Store
Real Landscapes • Valley Forest Unity Anset Store
SunTempkelamps Sun Temple Unity Asset Store
Dragon for Boss Monster: HP Unity Arset Store
Flooded Grounds Unity Asset Store
AbandonedSchool Animal Pack Deluxe Unity Asset Store
HQ Abandoned School (Modular) Unity Asset Store
SpaceShipDemo Space Ship Demo https://github.com/Unity-Technologies/SpaceshipDemo
Seaport2 Old Sea Port Unity Asset Store
Fantasy Monster - Skeleton Unity Asset Store
Dungeon Skeletons Demo Unity Asset Store
SceneAssets UsedSource
CB-ApocalypseCBU: Apocalypse EditionUnity Asset Store
 ULTIMATE ANIMATIONUnity Asset Store
 COLLECTION 
 Animal Pack DeluxeUnity Asset Store
 Customizable Survivors PackUnity Asset Store
SciFifacilitySci-Fi FacilityUnity Asset Store
 Robot Warnors CartoonUnity Asset Store
"Flooded Grounds
FloodedGrounds Bridges"Flooded GroundsUnity Asset Store
 Ghoul-zombieUnity Asset Store
 ZombieUnity Asset Store
 Fantastic Creature #1|Unity Asset Store
"SciFiBase
ScifiBaseNightStartStop
Sciti BaseStartStop"Sci-Fi baseUnity Asset Store
 Robot 1|Unity Asset Store
 Robot Warriors CartoonUnity Asset Store
 Robot SphereUnity Asset Store
Sun TempleSun TempleUnity Asset Store
 Animal Pack DeluxeUnity Asset Store
 Dragon for Boss Monster: HPUnity Asset Store
Sun TempkBushSun TempleUnity Asset Store
 Real Landscapes • Valley ForestUnity Anset Store
SunTempkelampsSun TempleUnity Asset Store
 Dragon for Boss Monster: HPUnity Arset Store
 Flooded GroundsUnity Asset Store
AbandonedSchoolAnimal Pack DeluxeUnity Asset Store
 HQ Abandoned School (Modular)Unity Asset Store
SpaceShipDemoSpace Ship Demohttps://github.com/Unity-TechnologiesSpaceshipDemo
Seaport2Old Sea PortUnity Asset Store
 Fantasy Monster - SkeletonUnity Asset Store
 Dungeon Skeletons DemoUnity Asset Store

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.
 

Qualcomm Rasterized Images for Super Resolution Processing Dataset License Agreement - Research Use

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.

 

Connect with our communities

Stay ahead of the curve

Receive the latest updates, exclusive offers, and valuable insights delivered through the Qualcomm newsletter straight to your inbox.

Stay ahead of the curve

Receive the latest updates, exclusive offers, and valuable insights delivered through the Qualcomm newsletter straight to your inbox.

Qualcomm relentlessly innovates to deliver intelligent computing everywhere, helping the world tackle some of its most important challenges. Our leading-edge AI, high performance, low-power computing, and unrivaled connectivity deliver proven solutions that transform major industries. At Qualcomm, we are engineering human progress.

Stay connected

Get the latest Qualcomm and industry information delivered to your inbox.

Subscribe
Manage your subscription

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patented technologies are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.