CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression

• URL: http://arxiv.org/abs/2403.08505v5
• Date: Sat, 08 Feb 2025 09:33:17 GMT
• Title: CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression
• Authors: Xinjie Zhang, Shenyuan Gao, Zhening Liu, Jiawei Shao, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Jun Zhang,
• Abstract summary: We propose a stereo image compression framework, named CAMSIC. CAMSIC transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model. Experiments show that our framework achieves state-of-the-art rate-distortion performance.
• Score: 15.819672238043786
• License:
• Abstract: Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and disparity dependencies, by introducing a novel content-aware masked image modeling (MIM) technique. Our content-aware MIM facilitates efficient bidirectional interaction between prior information and estimated tokens, which naturally obviates the need for an extra Transformer decoder. Experiments show that our stereo image codec achieves state-of-the-art rate-distortion performance on two stereo image datasets Cityscapes and InStereo2K with fast encoding and decoding speed. Code is available at https://github.com/Xinjie-Q/CAMSIC.

Related papers

• Stereo Image Coding for Machines with Joint Visual Feature Compression [69.28382442498408]
  The stereo image coding for machines (SICM) is formulated and explored in this paper. A machine vision-oriented stereo feature compression network (MVSFC-Net) is proposed for SICM. The proposed MVSFC-Net obtains superior compression efficiency as well as 3D visual task performance.
  arXiv  Detail & Related papers  (2025-02-20T01:46:17Z)
• When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding [118.72266141321647]
  Cross-Modality Video Coding (CMVC) is a pioneering approach to explore multimodality representation and video generative models in video coding. During decoding, previously encoded components and video generation models are leveraged to create multiple encoding-decoding modes. Experiments indicate that TT2V achieves effective semantic reconstruction, while IT2V exhibits competitive perceptual consistency.
  arXiv  Detail & Related papers  (2024-08-15T11:36:18Z)
• Image and Video Tokenization with Binary Spherical Quantization [36.850958591333836]
  We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ) BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. Our tokenizer uses a transformer encoder and decoder with simple block-wise causal masking to support variable-length videos as input.
  arXiv  Detail & Related papers  (2024-06-11T17:59:53Z)
• MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model [78.4051835615796]
  This paper proposes a method called Multimodal Image Semantic Compression. It consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. It can achieve optimal consistency and perception results while saving perceptual 50%, which has strong potential applications in the next generation of storage and communication.
  arXiv  Detail & Related papers  (2024-02-26T17:11:11Z)
• ECSIC: Epipolar Cross Attention for Stereo Image Compression [5.024813922014978]
  ECSIC achieves state-of-the-art performance in stereo image compression on the two popular stereo image datasets Cityscapes and InStereo2k.
  arXiv  Detail & Related papers  (2023-07-18T11:46:31Z)
• Neural Distributed Image Compression with Cross-Attention Feature Alignment [1.2234742322758418]
  We consider a pair of stereo images, which have overlapping fields of view, captured by a synchronized and calibrated pair of cameras. We assume that one image of the pair is to be compressed and transmitted, while the other image is available only at the decoder. In the proposed architecture, the encoder maps the input image to a latent space using a DNN, quantizes the latent representation, and compresses it losslessly using entropy coding.
  arXiv  Detail & Related papers  (2022-07-18T10:15:04Z)
• Video Coding Using Learned Latent GAN Compression [1.6058099298620423]
  We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video. Each frame is inverted in the latent space of StyleGAN, from which the optimal compression is learned.
  arXiv  Detail & Related papers  (2022-07-09T19:07:43Z)
• Towards End-to-End Image Compression and Analysis with Transformers [99.50111380056043]
  We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. We aim to redesign the Vision Transformer (ViT) model to perform image classification from the compressed features and facilitate image compression with the long-term information from the Transformer. Experimental results demonstrate the effectiveness of the proposed model in both the image compression and the classification tasks.
  arXiv  Detail & Related papers  (2021-12-17T03:28:14Z)
• Transformer-based Image Compression [18.976159633970177]
  Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. TIC rivals with state-of-the-art approaches including deep convolutional neural networks (CNNs) based learnt image coding (LIC) methods and handcrafted rules-based intra profile of recently-approved Versatile Video Coding (VVC) standard.
  arXiv  Detail & Related papers  (2021-11-12T13:13:20Z)
• Masked Autoencoders Are Scalable Vision Learners [60.97703494764904]
  Masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. Coupling these two designs enables us to train large models efficiently and effectively.
  arXiv  Detail & Related papers  (2021-11-11T18:46:40Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.