XeSS
E170408
XeSS (Xe Super Sampling) is Intel’s AI-driven upscaling technology designed to boost gaming performance and image quality by rendering at lower resolutions and reconstructing higher-resolution frames in real time.
All labels observed (5)
| Label | Occurrences |
|---|---|
| Intel XeSS | 4 |
| XeSS canonical | 2 |
| Xe Super Sampling | 1 |
| XeSS (Xe Super Sampling) | 1 |
| XeSS upscaling technology | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T1499546 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: XeSS Context triple: [Intel Arc, supports, XeSS]
-
A.
DLSS (Deep Learning Super Sampling)
DLSS (Deep Learning Super Sampling) is an NVIDIA graphics technology that uses deep learning to upscale lower-resolution images in real time, improving performance and visual quality in video games.
-
B.
PlayStation 5
PlayStation 5 is Sony’s ninth-generation home video game console known for its high-speed SSD, advanced graphics capabilities, and support for immersive features like ray tracing and 3D audio.
-
C.
RTX
RTX is NVIDIA's line of graphics technologies and products centered on real-time ray tracing and advanced GPU performance for gaming and professional visualization.
-
D.
RTX
RTX is a major American aerospace and defense company formed from the merger of Raytheon Company and United Technologies Corporation, known for its advanced military, aviation, and cybersecurity technologies.
-
E.
Xbox Cloud Gaming
Xbox Cloud Gaming is Microsoft’s cloud-based game streaming service that lets users play Xbox titles on various devices without needing a physical console.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: XeSS Target entity description: XeSS (Xe Super Sampling) is Intel’s AI-driven upscaling technology designed to boost gaming performance and image quality by rendering at lower resolutions and reconstructing higher-resolution frames in real time.
-
A.
DLSS (Deep Learning Super Sampling)
DLSS (Deep Learning Super Sampling) is an NVIDIA graphics technology that uses deep learning to upscale lower-resolution images in real time, improving performance and visual quality in video games.
-
B.
PlayStation 5
PlayStation 5 is Sony’s ninth-generation home video game console known for its high-speed SSD, advanced graphics capabilities, and support for immersive features like ray tracing and 3D audio.
-
C.
RTX
RTX is NVIDIA's line of graphics technologies and products centered on real-time ray tracing and advanced GPU performance for gaming and professional visualization.
-
D.
RTX
RTX is a major American aerospace and defense company formed from the merger of Raytheon Company and United Technologies Corporation, known for its advanced military, aviation, and cybersecurity technologies.
-
E.
Xbox Cloud Gaming
Xbox Cloud Gaming is Microsoft’s cloud-based game streaming service that lets users play Xbox titles on various devices without needing a physical console.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
AI-driven super sampling technology
ⓘ
image upscaling technology ⓘ spatial-temporal upscaling algorithm ⓘ |
| abbreviation | XeSS ⓘ |
| aimsTo |
increase frame rates
ⓘ
maintain or improve visual fidelity ⓘ |
| announcedAt | Intel Architecture Day 2021 ⓘ |
| announcedBy |
Intel
ⓘ
linked to:
Intel Corporation
|
| appliesTo |
3D graphics applications
ⓘ
PC games ⓘ |
| category |
game rendering technology
ⓘ
real-time graphics technology ⓘ |
| competesWith |
AMD FSR
ⓘ
linked to:
AMD FidelityFX Super Resolution
NVIDIA DLSS ⓘ
linked to:
DLSS (Deep Learning Super Sampling)
|
| designedFor |
Intel Arc GPUs
ⓘ
linked to:
Intel Arc
modern discrete GPUs ⓘ |
| developer |
Intel
ⓘ
linked to:
Intel Corporation
|
| feature |
anti-aliasing enhancement
ⓘ
image reconstruction from sub-native resolution ⓘ motion vector utilization ⓘ performance scaling modes ⓘ temporal data usage from previous frames ⓘ |
| fullName |
Xe Super Sampling
ⓘ
linked to:
XeSS
|
| improves |
detail reconstruction at high resolutions
ⓘ
perceived sharpness of images ⓘ |
| input |
depth buffer information
ⓘ
low-resolution rendered frame ⓘ motion vectors ⓘ |
| license | available to third-party developers ⓘ |
| operatesBy |
reconstructing higher-resolution frames in real time
ⓘ
rendering at lower internal resolution ⓘ |
| optimizationTarget |
gaming performance per watt
ⓘ
real-time rendering workloads ⓘ |
| output | upscaled frame at target resolution ⓘ |
| processingStage | post-processing stage in rendering pipeline ⓘ |
| purpose |
boost gaming performance
ⓘ
improve image quality in games ⓘ |
| releaseForm | SDK for game developers ⓘ |
| reliesOn | trained neural network models ⓘ |
| requires | game integration by developers ⓘ |
| supports |
4K gaming
ⓘ
high-resolution output ⓘ variable quality presets ⓘ |
| supportsHardware |
Intel Xe-HPG architecture
ⓘ
linked to:
Intel Arc
select non-Intel GPUs via DP4a path ⓘ |
| uses |
artificial intelligence
ⓘ
machine learning ⓘ neural network-based upscaling ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: XeSS Description of subject: XeSS (Xe Super Sampling) is Intel’s AI-driven upscaling technology designed to boost gaming performance and image quality by rendering at lower resolutions and reconstructing higher-resolution frames in real time.
Referenced by (9)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject linked to:
DLSS (Deep Learning Super Sampling)
linked to: XeSS
linked to: XeSS
linked to: XeSS
linked to: XeSS
linked to: XeSS