paper-with-me

Papers

LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Images

2025-06-22 · Chenyue Song, Chen Hui, Qing Lin, Wei zhang, Siqiao Li, Haiqi Zhu, Zhixuan Li, Shengping Zhang, Shaohui Liu, Feng Jiang, Xiang Li

Autoregressive Initial Bits is a framework that integrates sub-image autoregression and latent variable modeling, demonstrating its advantages in lossless medical image compression. However, in existing methods, the image segmentation process leads to an even distribution of latent variable information across each sub-image, which in turn causes posterior collapse and inefficient utilization of latent variables. To deal with these issues, we propose a prediction-based end-to-end lossless medical image compression method named LVPNet, leveraging global latent variables to predict pixel values and encoding predicted probabilities for lossless compression. Specifically, we introduce the Global Multi-scale Sensing Module (GMSM), which extracts compact and informative latent representations from the entire image, effectively capturing spatial dependencies within the latent space. Furthermore, to mitigate the information loss introduced during quantization, we propose the Quantization Compensation Module (QCM), which learns the distribution of quantization errors and refines the quantized features to compensate for quantization loss. Extensive experiments on challenging benchmarks demonstrate that our method achieves superior compression efficiency compared to state-of-the-art lossless image compression approaches, while maintaining competitive inference speed. The code is at https://github.com/scy-Jackel/LVPNet.

📄 PDF Abstract BibTeX arXiv:2506.17983

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionImage SegmentationQuantizationSemantic Segmentation

Similar Papers 제목 키워드 기반

Multiple Futures Prediction

2019-12-01 · NeurIPS 2019 12 · Charlie Tang, Russ R. Salakhutdinov

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcom…

motion predictionPrediction

Multiple Futures Prediction

2019-11-04 · Yichuan Charlie Tang, Ruslan Salakhutdinov

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcom…

motion predictionPrediction

Reduced-order modeling of unsteady fluid flow using neural network ensembles

2024-02-08 · Rakesh Halder, Mohammadmehdi Ataei, Hesam Salehipour, Krzysztof Fidkowski 외

The use of deep learning has become increasingly popular in reduced-order models (ROMs) to obtain low-dimensional representations of full-order models. Convolutional autoencoders (CAEs) are often used to this end as they…

Ensemble LearningPredictionTime SeriesTime Series Prediction

Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics

2019-12-23 · Jiayang Xu, Karthik Duraisamy

A data-driven framework is proposed towards the end of predictive modeling of complex spatio-temporal dynamics, leveraging nested non-linear manifolds. Three levels of neural networks are used, with the goal of predictin…

Temporal Sequences

A Latent Variable Framework for Scaling Laws in Large Language Models

2025-12-06 · Peiyao Cai, Chengyu Cui, Felipe Maia Polo, Seamus Somerstep 외 arxiv

We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures…