Timezone: »

 
Poster
Modality-Agnostic Variational Compression of Implicit Neural Representations
Jonathan Richard Schwarz · Jihoon Tack · Yee-Whye Teh · Jaeho Lee · Jinwoo Shin

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #636
in Poster Session 6 »

We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. This allows the specialisation of a shared INR network to each data item through subnetwork selection. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression. Variational Compression of Implicit Neural Representations (VC-INR) shows improved performance given the same representational capacity pre quantisation while also outperforming previous quantisation schemes used for other INR techniques.Our experiments demonstrate strong results over a large set of diverse modalities using the same algorithm without any modality-specific inductive biases. We show results on images, climate data, 3D shapes and scenes as well as audio and video, introducing VC-INR as the first INR-based method to outperform codecs as well-known and diverse as JPEG 2000, MP3 and AVC/HEVC on their respective modalities.

[ PDF]  [ Poster] 

Author Information

Jonathan Richard Schwarz (DeepMind)
Jihoon Tack (KAIST)
Yee-Whye Teh (Oxford and DeepMind)
Jaeho Lee (POSTECH)
Jinwoo Shin (KAIST)

More from the Same Authors