3 papers
cs.CV2025
MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
Dominik Zimny, Artur Kasymov, Adam Kania +4
NeRF is a popular model that efficiently represents 3D objects from 2D images. However, vanilla NeRF has some important limitations. NeRF must be trained on each object separately.…
cs.CV2024
HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
Adam Kania, Artur Kasymov, Jakub KoÅciukiewicz +4
The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated…
cs.LG2024
HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks
M. PrzewiÄźlikowski, P. Przybysz, J. Tabor +2
The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-S…