Consistent Generative Query Networks

42 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Neural Processes (2018, background): “Consistent GQN (CGQN) is an extension of GQN that focuses on generating consistent samples and is thus also closely related to NPs (Kumar et al., 2018).”
Attentive Neural Processes (2019, background): “Generative Query Networks (Eslami et al., 2018; Kumar et al., 2018) are models for spatial prediction that render a frame of a scene given a viewpoint.”
Transframer: Arbitrary Frame Prediction with Generative Models (2022, background): “Some of the tasks we consider, such as novel view synthesis and video generation have previously been expressed in this manner [18,35].”
On the Limitations of Representing Functions on Sets (2019, background): “Generative Query Networks (Eslami et al., 2018; Kumar et al., 2018) can be regarded as an instantiation of neural processes to learn useful representations of 3D scenes from multiple 2D views.”
ROOTS: Object-Centric Representation and Rendering of 3D Scenes (2020, methodology): “For scene-level representation and generation quality, we use CGQN (Kumar et al., 2018) as the baseline model, and refer to it as GQN in the rest of this section to indicate the general GQN framework.”