no code implementations • 5 Dec 2023 • Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz, Emilien Dupont
On the UVG video benchmark, we match the RD performance of the Video Compression Transformer (Mentzer et al.), a well-established neural video codec, with less than 5k MACs/pixel for decoding.
no code implementations • 6 Feb 2023 • Matthias Bauer, Emilien Dupont, Andy Brock, Dan Rosenbaum, Jonathan Richard Schwarz, Hyunjik Kim
Neural fields, also known as implicit neural representations, have emerged as a powerful means to represent complex signals of various modalities.
1 code implementation • 30 Jan 2022 • Emilien Dupont, Hrushikesh Loya, Milad Alizadeh, Adam Goliński, Yee Whye Teh, Arnaud Doucet
Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities.
1 code implementation • 28 Jan 2022 • Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami, Danilo Rezende, Dan Rosenbaum
A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location.
1 code implementation • ICLR Workshop Neural_Compression 2021 • Emilien Dupont, Adam Goliński, Milad Alizadeh, Yee Whye Teh, Arnaud Doucet
We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image.
1 code implementation • 9 Feb 2021 • Emilien Dupont, Yee Whye Teh, Arnaud Doucet
By treating data points as functions, we can abstract away from the specific type of data we train on and construct models that are agnostic to discretization.
1 code implementation • 20 Dec 2020 • Michael Hutchinson, Charline Le Lan, Sheheryar Zaidi, Emilien Dupont, Yee Whye Teh, Hyunjik Kim
Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing.
no code implementations • NeurIPS 2020 • Arnab Ghosh, Harkirat Behl, Emilien Dupont, Philip Torr, Vinay Namboodiri
Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive.
no code implementations • 18 Jun 2020 • Arnab Ghosh, Harkirat Singh Behl, Emilien Dupont, Philip H. S. Torr, Vinay Namboodiri
Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive.
1 code implementation • ICML 2020 • Emilien Dupont, Miguel Angel Bautista, Alex Colburn, Aditya Sankar, Carlos Guestrin, Josh Susskind, Qi Shan
We propose a framework for learning neural scene representations directly from images, without 3D supervision.
6 code implementations • NeurIPS 2019 • Emilien Dupont, Arnaud Doucet, Yee Whye Teh
We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent.
Ranked #22 on Image Classification on MNIST
2 code implementations • 8 Oct 2018 • Emilien Dupont, Suhas Suresha
Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics.
4 code implementations • NeurIPS 2018 • Emilien Dupont
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner.
1 code implementation • 8 Feb 2018 • Emilien Dupont, Tuanfeng Zhang, Peter Tilke, Lin Liang, William Bailey
An important problem in geostatistics is to build models of the subsurface of the Earth given physical measurements at sparse spatial locations.