The JPEG 2000 still image compression standard

By Athanassios N. Skodras, Charilaos A. Christopoulos, Touradj Ebrahimi. IEEE Signal Processing Magazine, 2001

2,092 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2beb0e5650dde462da27056b4cfdd8281e7130f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Dacheng Tao
4. Ming-Hsuan Yang
5. Trevor Darrell
6. Yi Yang
7. Wanli Ouyang
8. Jitendra Malik

Citations in the corpus

• Wavelets and their applications (2007, methodology): “We will not cover here the processing of such images (for additional information see [SKO 01]).”
• DVC: An End-To-End Deep Video Compression Framework (2018, methodology): “Recently, deep neural network (DNN) based autoencoder for image compression [34, 11, 35, 8, 12, 19, 33, 21, 28, 9] has achieved comparable or even better performance than the traditional image codecs like JPEG [37], JPEG2000 [29] or BPG [1].”
• A survey of multimedia streaming in wireless sensor networks (2008, methodology): “JPEG 2000 [13] and accordingly employ wavelet transform”
• The dual-tree complex wavelet transform (2005, background): “The sparsity of the wavelet coefficients of many real-world signals enables near-optimal signal processing based on simple thresholding (keep the large coefficients and kill the small ones), the core of a host of powerful image compression (JPEG2000 [98]), denoising, approximation, and deterministic”
• Scaling and evaluating sparse autoencoders (2024, neutral): “In a progressive code, a partial transmission still allows reconstructing the signal with reasonable fidelity [Skodras et al., 2001].”
• Lossy Image Compression with Compressive Autoencoders (2017, methodology): “We compared our method to JPEG (Wallace, 1991), JPEG 2000 (Skodras et al., 2001), and the RNN-based method of (Toderici et al., 2016b) 4 .”
• Directionlets: anisotropic multidirectional representation with separable filtering (2006, background): “These are the main reasons why it has been adopted in the image compression standard JPEG-2000 [3].”
• Improving Inference for Neural Image Compression (2020, methodology): “[M9] JPEG 2000 Classical lossy image compression method [Adams, 2001].”
• QARV: Quantization-Aware ResNet VAE for Lossy Image Compression (2023, methodology): “In conventional image codecs such as the JPEG [17], JPEG 2000 [18], and VVC intra [19], an orthogonal linear transformation such as discrete cosine transform or discrete wavelet transform is applied to convert image pixels into transform co-efficients.”
• A tutorial on modern lossy wavelet image compression: foundations of JPEG 2000 (2001, methodology): “The focus of this discussion is on the fundamental principles of wavelet coding and not the actual standard itself (more details on the standard can be found in [2]).”
• NeRV: Neural Representations for Videos (2021, methodology): “Before the resurgence of deep networks, handcrafted image compression techniques, like JPEG [18] and JPEG2000 [19], were widely used.”