444 citations · 1.3k across the 22 of their papers we have counts for
3 papers · 1 filter
Detecting Cloud Presence in Satellite Images Using the RGB-based CLIP Vision-Language Model
Mikolaj Czerkawski, Robert Atkinson, Christos Tachtatzis
This work explores capabilities of the pre-trained CLIP vision-language model to identify satellite images affected by clouds. Several approaches to using the model to perform clou…
Neural Weight Step Video Compression
Mikolaj Czerkawski, Javier Cardona, Robert Atkinson +4
A variety of compression methods based on encoding images as weights of a neural network have been recently proposed. Yet, the potential of similar approaches for video compression…
Neural Knitworks: Patched Neural Implicit Representation Networks
Mikolaj Czerkawski, Javier Cardona, Robert Atkinson +4
Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applicatio…