paper-with-me

홈 › Papers

Learned Image Compression with Mixed Transformer-CNN Architectures

2023-03-27 · CVPR 2023 1 · Jinming Liu, Heming Sun, Jiro Katto

Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards. Most existing LIC methods are Convolutional Neural Networks-based (CNN-based) or Transformer-based, which have different advantages. Exploiting both advantages is a point worth exploring, which has two challenges: 1) how to effectively fuse the two methods? 2) how to achieve higher performance with a suitable complexity? In this paper, we propose an efficient parallel Transformer-CNN Mixture (TCM) block with a controllable complexity to incorporate the local modeling ability of CNN and the non-local modeling ability of transformers to improve the overall architecture of image compression models. Besides, inspired by the recent progress of entropy estimation models and attention modules, we propose a channel-wise entropy model with parameter-efficient swin-transformer-based attention (SWAtten) modules by using channel squeezing. Experimental results demonstrate our proposed method achieves state-of-the-art rate-distortion performances on three different resolution datasets (i.e., Kodak, Tecnick, CLIC Professional Validation) compared to existing LIC methods. The code is at https://github.com/jmliu206/LIC_TCM.

📄 PDF Abstract BibTeX arXiv:2303.14978

Code (3)

jmliu206/lic_tcm 공식 구현 pytorch
Nikolai10/LIC-TCM tf
fengyurenpingsheng/WeConvene pytorch

Tasks

Image Compression

Similar Papers 제목 키워드 기반

Bi-Level Spatial and Channel-aware Transformer for Learned Image Compression

2024-08-07 · Hamidreza Soltani, Erfan Ghasemi

Recent advancements in learned image compression (LIC) methods have demonstrated superior performance over traditional hand-crafted codecs. These learning-based methods often employ convolutional neural networks (CNNs) o…

Image Compression

DepthTCM: High Efficient Depth Compression via Physics-aware Transformer-CNN Mixed Architecture

2026-03-22 · Young-Seo Chang, Yatong An, Jae-Sang Hyun arxiv

We propose DepthTCM, a physics-aware end-to-end framework for depth map compression. In our framework of DepthTCM, the high-bit depth map is first converted to a conventional 3-channel image representation losslessly usi…

Image Compression using only Attention based Neural Networks

2023-10-17 · Natacha Luka, Romain Negrel, David Picard

In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates. While existing methods incorporate convolutional priors w…

Image CompressionQuantization

Window-based Channel Attention for Wavelet-enhanced Learned Image Compression

2024-09-21 · Heng Xu, Bowen Hai, Yushun Tang, Zhihai He

Learned Image Compression (LIC) models have achieved superior rate-distortion performance than traditional codecs. Existing LIC models use CNN, Transformer, or Mixed CNN-Transformer as basic blocks. However, limited by t…

Image Compression

Human Aligned Compression for Robust Models

2025-04-16 · Samuel Räber, Andreas Plesner, Till Aczel, Roger Wattenhofer

Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, c…