Related papers: CIC: Circular Image Compression
The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing…
Single image inverse problem is a notoriously challenging ill-posed problem that aims to restore the original image from one of its corrupted versions. Recently, this field has been immensely influenced by the emergence of deep-learning…
Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior…
Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support…
Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed…
Linear transformations are cornerstone operations utilized in modern computing, but are computationally expensive on current electronic platforms. Optical computing has been positioned as a new computing solution, promising high speed and…
The rapid development of AR/VR, remote sensing, satellite radar, and medical equipment has created an imperative demand for ultra efficient image compression and reconstruction that exceed the capabilities of electronic processors. For the…
Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images. The high effort and cost required for labeling…
How to represent an image? While the visual world is presented in a continuous manner, machines store and see the images in a discrete way with 2D arrays of pixels. In this paper, we seek to learn a continuous representation for images.…
Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired…
Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets…
In this paper, we present an approach, namely Lexical Semantic Image Completion (LSIC), that may have potential applications in art, design, and heritage conservation, among several others. Existing image completion procedure is highly…
Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference. CIR is inherently an instruction-following task, as…
The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors can be utilized to synthesize textures during inverse…
CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…
The large amount of data collected by LiDAR sensors brings the issue of LiDAR point cloud compression (PCC). Previous works on LiDAR PCC have used range image representations and followed the predictive coding paradigm to create a basic…
CLIC is a proposed linear e+e- collider designed to provide particle collisions at center-of-mass energies of up to 3 TeV. Precise measurements of the properties of the top quark and the Higgs boson, as well as searches for Beyond the…
Despite the unprecedented compression efficiency achieved by deep learned image compression (LIC), existing methods usually approximate the desired bitrate by adjusting a single quality factor for a given input image, which may compromise…
Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms…
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical…