Joint Global and Local Hierarchical Priors for Learned Image Compression

2021-12-08 · CVPR 2022 1 · Jun-Hyuk Kim, Byeongho Heo, Jong-Seok Lee

Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like other vision tasks, most recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling long-range dependencies due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To overcome this issue, we propose a novel entropy model called Information Transformer (Informer) that exploits both global and local information in a content-dependent manner using an attention mechanism. Our experiments show that Informer improves rate--distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem. Our source code is available at https://github.com/naver-ai/informer.

📄 PDF Abstract BibTeX arXiv:2112.04487

Code (1)

naver-ai/informer 공식 구현 pytorch

Tasks

Image Compression

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors

2021-04-01 · CVPR 2021 1 · Jan Bechtold, Maxim Tatarchenko, Volker Fischer, Thomas Brox

Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on learned global shape priors and, hence,…

3D Object Reconstruction 3D Reconstruction Hallucination Object Reconstruction+1

Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints

2025-11-13 · Xiangyue Zhang, Jianfang Li, Jianqiang Ren, Jiaxu Zhang arxiv

Reliable co-speech motion generation requires precise motion representation and consistent structural priors across all joints. Existing generative methods typically operate on local joint rotations, which are defined hi…

Deep Learning Shape Priors for Object Segmentation

2013-06-01 · CVPR 2013 6 · Fei Chen, Huimin Yu, Roland Hu, Xunxun Zeng

In this paper we introduce a new shape-driven approach for object segmentation. Given a training set of shapes, we first use deep Boltzmann machine to learn the hierarchical architecture of shape priors. This learned hie…

Deep Learning Object Semantic Segmentation

HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression

2026-03-06 · Haoxuan Xiong, Yuanyuan Xu, Kun Zhu, Yiming Wang 외 arxiv

Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing methods predominantly exploit internal con…