Modality-Agnostic Variational Compression of Implicit Neural Representations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data CompressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representation (INR)-based approaches: it avoids quan…
Data CompressionQuantizationLINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression
Existing AI-based point cloud compression methods struggle with dependence on specific training data distributions, which limits their real-world deployment. Implicit Neural Representation (INR) methods solve the above p…
DecoderModel CompressionIncomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis
Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modaliti…
DiagnosticL$_0$onie: Compressing COINs with L$_0$-constraints
Advances in Implicit Neural Representations (INR) have motivated research on domain-agnostic compression techniques. These methods train a neural network to approximate an object, and then store the weights of the traine…
Compression with Bayesian Implicit Neural Representations
Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image. Based on this view, data can be compressed by overfitting a …
Audio CompressionQuantization