Related papers: Predicting Chroma from Luma in AV1
Modern video codecs including the newly developed AOMedia Video 1 (AV1) utilize hybrid coding techniques to remove spatial and temporal redundancy. However, efficient exploitation of statistical dependencies measured by a mean squared error…
We combine a high-resolution hydro-simulation of the LambdaCDM cosmology with two radiative transfer schemes (for continuum and line radiation) to predict the properties, spectra and spatial distribution of fluorescent Ly-alpha emission at…
Conventional video encoders typically employ a fixed chroma subsampling format, such as YUV420, which may not optimally reflect variations in chroma detail across different types of content. This can lead to suboptimal chroma quality and…
Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal…
Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can…
With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs has become increasingly important. Existing VLMs predominantly digest and understand…
We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data…
Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional…
Rapidly increasing demand for high speed data is pushing 6G wireless networks to support larger link scales, lower latency, and higher spectral efficiency. Visible light communications (VLC) is a strong complement to radio frequency (RF)…
This paper introduces a new machine learning-assisted chromatic dispersion compensation filter, demonstrating its superior power efficiency compared to conventional FFT-based filters for metro link distances. Validations on FPGA confirmed…
Latent inpainting in diffusion models still relies almost universally on linearly interpolating VAE latents under a downsampled mask. We propose a key principle for compositing image latents: Pixel-Equivalent Latent Compositing (PELC). An…
Despite the vast success of standard planar convolutional neural networks, they are not the most efficient choice for analyzing signals that lie on an arbitrarily curved manifold, such as a cylinder. The problem arises when one performs a…
Actively tunable optical filters based on chalcogenide phase-change materials (PCMs) are an emerging technology with applications across chemical spectroscopy and thermal imaging. The refractive index of an embedded PCM thin film is…
Recent advances in video compression have seen significant coding performance improvements with the development of new standards and learning-based video codecs. However, most of these works focus on application scenarios that allow a…
This paper investigates methods for calculating the chromatic symmetric function (CSF) of a graph in chromatic-bases and the $m_\lambda$-basis. Our key contributions include a novel approach for calculating the CSF in chromatic-bases…
In the past decade, SIFT descriptor has been witnessed as one of the most robust local invariant feature descriptors and widely used in various vision tasks. Most traditional image classification systems depend on the luminance-based SIFT…
We simulate the flux emitted from galaxy halos in order to quantify the brightness of the circumgalactic medium (CGM). We use dedicated zoom-in cosmological simulations with the hydrodynamical Adaptive Mesh Refinement code RAMSES, which are…
Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring the model to implicitly recover the unmixing process to obtain…
CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…
In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules…