Sorry, you need to enable JavaScript to visit this website.

Supplementary Materials for "RETHINKING IMAGE HISTOGRAM MATCHING FOR IMAGE CLASSIFICATION"

Supplementary Materials for "When 512x512 Is Not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution"

Supplementary Materials for "When 512x512 Is Not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution"

The task of gradient magnitude image construction for hyperspectral images (HSI) is currently under-explored, with most approaches in use being naive extensions of gradients, originally proposed for color images. But HSI showcase principal differences from color or multispectral images in that their pixels register consecutive narrow bands of the electromagnetic spectrum, thus approximating a continuous signal, instead of a few wide discrete bands. We propose three novel gradient calculation approaches for HSI.

There's been a surge in adoption of video conferencing applications for both personal and business use cases. However, there are millions of people around the world who are unable to truly enjoy these technologies due to bandwidth limitations despite having appropriate hardware. Deep learning offers a solution for enhancing low bitrate videos but most models today are either hard to incorporate with modern compression standards or require specialized hardware to run such as GPUs making these models impractical.

Intrinsic image decomposition (IID) is the task of separating an image into albedo and shade. In real-world scenes, it is difficult to quantitatively assess IID quality due to the unavailability of ground truth. The existing method provides the relative reflection intensities based on human-judged annotations. However, these annotations have challenges in subjectivity, relative evaluation, and hue non-assessment.

just testing

This zip folder contains the Supplementary Material of the paper RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks, submitted to ICIP 2025.

This .pdf file provides supplementary information of the paper ”Harnessing the Power of LLMs for Image Aesthetics Assessment through Semantic and Contextual Understanding”.

Supplementary Materials for SIAvatar: Animatable 3D Gaussian Avatar from a Single Image