Related papers: Evaluating Strong Idempotence of Image Codec
Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…
Overfitted codecs compress an image by learning a decoder tailored to the content during the encoding. As such, they trade increased encoding complexity for strong compression performance and low decoding complexity. This work introduces…
Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However, standard…
Underwater images often suffer from quality degradation due to absorption and scattering effects. Most existing underwater image enhancement algorithms produce a single, fixed-color image, limiting user flexibility and application. To…
Bi-modal (respectively, multi-modal) constrained coding refers to an encoding model whereby a user input block can be mapped to two (respectively, multiple) codewords. In current storage applications, such as optical disks, multi-modal…
Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to their difficulty…
We consider a network of two nodes separated by a noisy channel with two-sided state information, in which the input and output signals have to be coordinated with the source and its reconstruction. In the case of non-causal encoding and…
This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to generate captions from masked images, closely resembling the…
Previous research contributions on blind lossy compression identification report near perfect performance metrics on their test set, across a variety of codecs and bit rates. However, we show that such results can be deceptive and may not…
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a…
Multi-view image compression plays a critical role in 3D-related applications. Existing methods adopt a predictive coding architecture, which requires joint encoding to compress the corresponding disparity as well as residual information.…
Using the EXIT chart approach, a necessary and sufficient condition is developed for the local stability of iterative decoding of multi-edge type (MET) doubly-generalized low-density parity-check (D-GLDPC) code ensembles. In such code…
Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…
Large language models and deep learning models designed for code intelligence have revolutionized the software engineering field due to their ability to perform various code-related tasks. These models can process source code and software…
Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video…
High Efficiency Video Coding (HEVC) has doubled the video compression ratio with equivalent subjective quality as compared to its predecessor H.264/AVC. The significant coding efficiency improvement is attributed to many new techniques.…
With the development of large models, watermarks are increasingly employed to assert copyright, verify authenticity, or monitor content distribution. As applications become more multimodal, the utility of watermarking techniques becomes…
Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition…
In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This…