LiVeAction is a lightweight asymmetric neural codec using an FFT-inspired encoder and variance-based training that outperforms generative tokenizers in rate-distortion while supporting real-time use on resource-constrained sensors across modalities.
hub
Compressai: a pytorch library and evaluation platform for end-to-end compression research
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
representative citing papers
S2-CoT coordinates a Structural Fidelity Adapter in the encoder-decoder with a Semantic Context Adapter in the entropy model to convert potential performance loss into state-of-the-art gains across base codecs while using only a small fraction of parameters.
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS reduction over DCVC-RT.
FAJSCC is a new deepJSCC architecture for images that achieves better transmission performance with lower complexity than prior models and enables independent encoder-decoder compute adjustment.
EF-LIC is a multi-rate learned image compression framework that eliminates entropy coding via unconstrained VQ and autoregressive reparameterization, achieving up to 67.86% bitrate reduction versus MS-ILLM on Kodak with LPIPS while running over 3x faster at encode and 5x at decode.
TAFA-GSGC is a scalable point cloud geometry compression codec using progressive residual refinement and group-wise entropy coding that achieves average BD-rate reductions of 4.99% (D1-PSNR) and 5.92% (D2-PSNR) over PCGCv2 while supporting monotonic multi-quality decoding from a single bitstream.
Gaussian Shannon models diffusion as a noisy channel and uses error-correcting codes plus majority voting to recover watermark bits exactly from perturbed AI-generated images.
HR3L enables robust remote RL training over unreliable channels via homomorphic state encoding without gradient exchange, outperforming prior methods in sample efficiency and adapting to packet loss, delays, and bandwidth limits.
Adaptive transform coding for semantic feature compression, motivated by the conditional rate-distortion function of a Gaussian mixture model, outperforms or matches neural compression methods on vision backbone features while remaining flexible and interpretable.
An intention-aware semantic agent system for AI glasses reduces bandwidth by over 50% in simulations while preserving task performance through adaptive preprocessing guided by inferred user intentions.
Autoencoder CSI compression reduces channel sounding overhead by more than 50% versus standard IEEE 802.11 methods and improves throughput and latency in coordinated beamforming.
Sequential encoder-decoder distillation provides robust initialization for lightweight image compression autoencoders, followed by standard training that preserves reconstruction quality better than direct optimization in early epochs.
Auxiliary loss applied to the encoder in learned ICM models produces 27.7% and 20.3% BD-rate improvements for object detection and semantic segmentation versus standard training.
citing papers explorer
-
LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation
LiVeAction is a lightweight asymmetric neural codec using an FFT-inspired encoder and variance-based training that outperforms generative tokenizers in rate-distortion while supporting real-time use on resource-constrained sensors across modalities.
-
What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters
S2-CoT coordinates a Structural Fidelity Adapter in the encoder-decoder with a Semantic Context Adapter in the entropy model to convert potential performance loss into state-of-the-art gains across base codecs while using only a small fraction of parameters.
-
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS reduction over DCVC-RT.
-
Feature Importance-Aware Deep Joint Source-Channel Coding for Computationally Efficient and Adjustable Image Transmission
FAJSCC is a new deepJSCC architecture for images that achieves better transmission performance with lower complexity than prior models and enables independent encoder-decoder compute adjustment.
-
Efficient Learned Image Compression without Entropy Coding
EF-LIC is a multi-rate learned image compression framework that eliminates entropy coding via unconstrained VQ and autoregressive reparameterization, achieving up to 67.86% bitrate reduction versus MS-ILLM on Kodak with LPIPS while running over 3x faster at encode and 5x at decode.
-
TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement
TAFA-GSGC is a scalable point cloud geometry compression codec using progressive residual refinement and group-wise entropy coding that achieves average BD-rate reductions of 4.99% (D1-PSNR) and 5.92% (D2-PSNR) over PCGCv2 while supporting monotonic multi-quality decoding from a single bitstream.
-
Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
Gaussian Shannon models diffusion as a noisy channel and uses error-correcting codes plus majority voting to recover watermark bits exactly from perturbed AI-generated images.
-
Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding
HR3L enables robust remote RL training over unreliable channels via homomorphic state encoding without gradient exchange, outperforming prior methods in sample efficiency and adapting to packet loss, delays, and bandwidth limits.
-
Adaptive Transform Coding for Semantic Compression
Adaptive transform coding for semantic feature compression, motivated by the conditional rate-distortion function of a Gaussian mixture model, outperforms or matches neural compression methods on vision backbone features while remaining flexible and interpretable.
-
Intention-Aware Semantic Agent Communications for AI Glasses
An intention-aware semantic agent system for AI glasses reduces bandwidth by over 50% in simulations while preserving task performance through adaptive preprocessing guided by inferred user intentions.
-
Autoencoder-Based CSI Compression for Beyond Wi-Fi 8 Coordinated Beamforming
Autoencoder CSI compression reduces channel sounding overhead by more than 50% versus standard IEEE 802.11 methods and improves throughput and latency in coordinated beamforming.
-
Efficient training for compact compression models via sequential distillation
Sequential encoder-decoder distillation provides robust initialization for lightweight image compression autoencoders, followed by standard training that preserves reconstruction quality better than direct optimization in early epochs.
-
Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss
Auxiliary loss applied to the encoder in learned ICM models produces 27.7% and 20.3% BD-rate improvements for object detection and semantic segmentation versus standard training.