Recent advancements in image compression are focusing on enhancing efficiency and fidelity across various applications, particularly in high-resolution and remote sensing contexts. Techniques such as structured Gaussian representations and conditional diffusion models are being refined to achieve significant compression ratios while preserving critical details, with some methods reporting up to 21.2x compression on drone imagery. The integration of joint super-resolution and adaptive bitrate control is also gaining traction, allowing for flexible image restoration across varying compression levels. Additionally, hardware implementations, like FPGA designs for JPEG XS, are addressing computational challenges, promoting practical deployment in low-latency environments. The shift towards leveraging temporal priors and frequency-aware refinements indicates a growing emphasis on optimizing both the speed and quality of image reconstruction, which is crucial for applications in urban monitoring and disaster assessment, where large datasets pose significant storage and management challenges. Overall, the field is moving towards more sophisticated, adaptable solutions that balance compression efficiency with perceptual quality.
2D Gaussian Splatting has emerged as a novel image representation technique that can support efficient rendering on low-end devices. However, scaling to high-resolution images requires optimizing and ...
Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transformers, which are inher...
Recent diffusion-based extreme image compression methods have demonstrated remarkable performance at ultra-low bitrates. However, most approaches require training separate diffusion models for each ta...
Raw images preserve linear sensor measurements and high bit-depth information crucial for advanced vision tasks and photography applications, yet their storage remains challenging due to large file si...
Existing remote sensing image compression methods still explore to balance high compression efficiency with the preservation of fine details and task-relevant information. Meanwhile, high-resolution d...
Recent advancements in diffusion-based generative priors have enabled visually plausible image compression at extremely low bit rates. However, existing approaches suffer from slow sampling processes ...
Recently, progress has been made on the Intra Pattern Copy (IPC) tool for JPEG XS, an image compression standard designed for low-latency and low-complexity coding. IPC performs wavelet-domain intra c...
We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an explicit intermediate ...