Data-Driven Hallucination of Different Views
E326787
"Data-Driven Hallucination of Different Views" is a computer vision research work by Alexei Efros that uses data-driven techniques to synthesize plausible novel viewpoints of a scene from a single or limited set of images.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Data-Driven Hallucination of Different Views canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3094203 — 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: Data-Driven Hallucination of Different Views Context triple: [Alexei Efros, notableWork, Data-Driven Hallucination of Different Views]
-
A.
StyleGAN
StyleGAN is a state-of-the-art generative adversarial network architecture known for producing highly realistic, controllable images by manipulating disentangled style representations at different layers of the network.
-
B.
Deep Convolutional GAN
Deep Convolutional GAN is a widely used GAN architecture that replaces fully connected layers with deep convolutional layers to generate high-quality, realistic images.
-
C.
Conditional GAN
A Conditional GAN is a type of generative adversarial network that produces data samples conditioned on auxiliary information such as class labels or input images, enabling controlled and targeted generation.
-
D.
Fréchet Inception Distance
Fréchet Inception Distance is a widely used quantitative metric that measures the similarity between real and generated images by comparing their feature distributions extracted from a pretrained Inception network.
-
E.
Progressive GAN
Progressive GAN is a generative adversarial network architecture that grows both the generator and discriminator layers progressively during training to produce high-resolution, high-quality synthetic images.
- 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: Data-Driven Hallucination of Different Views Target entity description: "Data-Driven Hallucination of Different Views" is a computer vision research work by Alexei Efros that uses data-driven techniques to synthesize plausible novel viewpoints of a scene from a single or limited set of images.
-
A.
StyleGAN
StyleGAN is a state-of-the-art generative adversarial network architecture known for producing highly realistic, controllable images by manipulating disentangled style representations at different layers of the network.
-
B.
Deep Convolutional GAN
Deep Convolutional GAN is a widely used GAN architecture that replaces fully connected layers with deep convolutional layers to generate high-quality, realistic images.
-
C.
Conditional GAN
A Conditional GAN is a type of generative adversarial network that produces data samples conditioned on auxiliary information such as class labels or input images, enabling controlled and targeted generation.
-
D.
Fréchet Inception Distance
Fréchet Inception Distance is a widely used quantitative metric that measures the similarity between real and generated images by comparing their feature distributions extracted from a pretrained Inception network.
-
E.
Progressive GAN
Progressive GAN is a generative adversarial network architecture that grows both the generator and discriminator layers progressively during training to produce high-resolution, high-quality synthetic images.
- F. None of above. chosen
Statements (30)
| Predicate | Object |
|---|---|
| instanceOf |
computer vision research work
ⓘ
research paper ⓘ |
| aimsTo | synthesize plausible novel viewpoints of a scene ⓘ |
| approach |
example-based synthesis
ⓘ
non-parametric data-driven modeling ⓘ |
| assumption | visual world contains recurring patterns that can be reused for hallucination ⓘ |
| author |
Alexei Efros
ⓘ
surface form:
Alexei A. Efros
Alexei Efros ⓘ |
| category | academic research ⓘ |
| contribution |
demonstrates that plausible new views can be synthesized without explicit 3D geometry
ⓘ
shows effectiveness of data-driven priors for view synthesis ⓘ |
| field |
computer vision
ⓘ
image-based rendering ⓘ view synthesis ⓘ |
| focusesOn | plausibility of synthesized views rather than exact geometric accuracy ⓘ |
| goal | generate visually consistent new viewpoints from limited data ⓘ |
| influencedBy | non-parametric texture synthesis methods ⓘ |
| input |
limited set of images of a scene
ⓘ
single image of a scene ⓘ |
| language | English ⓘ |
| output | novel views of the scene ⓘ |
| relatedTo |
3D perception from 2D images
ⓘ
image hallucination ⓘ scene reconstruction ⓘ texture synthesis ⓘ |
| relatedWorkOf | Alexei A. Efros research on example-based image synthesis ⓘ |
| task | novel view synthesis from sparse observations ⓘ |
| topic |
hallucination of unseen content in images
ⓘ
learning-based image synthesis ⓘ |
| usesMethod | data-driven techniques ⓘ |
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: Data-Driven Hallucination of Different Views Description of subject: "Data-Driven Hallucination of Different Views" is a computer vision research work by Alexei Efros that uses data-driven techniques to synthesize plausible novel viewpoints of a scene from a single or limited set of images.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.