3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in foveation-9
No benchmarks available.
Use these libraries to find foveation-9 models and implementations
No datasets available.
No subtasks available.
The Deep Recurrent Attentive Writer neural network architecture for image generation substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.
Evidence is found that foveated perceptual systems learn a visual representation that is distinct from non-foveation perceptual systems, with implications in generalization, robustness, and perceptual sensitivity, which provides computational support for the idea that the foveate nature of the human visual system might confer a functional advantage for scene representation.
The Deep Co-attention based Comparators (DCCs) that fuse the co-dependent representations of the paired images so as to focus on the relevant parts of both images and produce their relative representations are introduced.
Foveation module is introduced, a learnable "dataloader" which, for a given ultra-high resolution image, adaptively chooses the appropriate configuration (FoV/resolution trade-off) of the input patch to feed to the downstream segmentation model at each spatial location of the image.
This paper demonstrates how a GPU, with a CUDA block-wise architecture, can be employed for radially-variant rendering, with opportunities for more complex post-processing to ensure a metameric foveation scheme.
An end-to-end differentiable foveated active vision architecture that leverages a graph convolutional network to process foveation images, and a simple yet effective formulation for foveate image sampling is introduced.
Adding a benchmark result helps the community track progress.