GitHub

Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization (ECCV2024)

(2024-9-4) PASD-SDXL are now publicly available. Please have a try via python3 test_pasd_sdxl.py! (2024-8-15) PASD-SDXL will be released soon. It surpasses the PASD ...

Designers Reveal the “75% Rule” That Instantly Makes Small, Cramped Rooms Feel Huge

Interior designers are moving beyond the accent wall in favor of the 75% color drench — a paint technique that makes rooms ...

Matisse Blue by Nataliya Naymark Wins Bronze in A’ Design Award

Nataliya Naymark Receives Bronze A' Design Award in Lighting Products and Fixtures Design for Matisse Blue COMO, CO, ...

Designers Say This Is the Most Important Step to Picking the Right Paint Color

These designer tips on choosing a paint color can help you make a decision on your new wall color. Here's what to consider ...
IEEE Spectrum on MSN

Two e-paper engineers keep turning to the wisdom of the crowd

After dev kit success, Modos’ cofounders offer an e-paper monitor ...
the-decoder

Microsoft Research's Mirage gives video generation a persistent spatial memory that doesn't forget what's around the corner

Mirage is a new video world model that skips the costly detour through pixel-based memory. That speeds up generation and keeps a scene's spatial structure stable even during long camera moves.
IEEE

Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion Models

Abstract: Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle ...
Quanta Magazine

Researchers Uncover Hidden Ingredients Behind AI Creativity

Image generators are designed to mimic their training data, so where does their apparent creativity come from? A recent study suggests that it’s an inevitable by-product of their architecture. We were ...
GitHub

LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement (PR 2025)

[2025/7/14] 🔥 Release our Real-world Tesing dataset for real-world LLIE! [2025/7/14] 🔥 Release the Pre trained models! [2025/7/14] 🔥 Release the codes! [2025/3/21] 🔥 Paper accepted at PR 2025 ...
IEEE

Learning Shape-Color Diffusion Priors for Text-Guided 3D Object Generation

Abstract: Generating 3D shapes according to specific textual input is a crucial topic in the multimedia application, with its potential enhancement to the VR/AR/XR usage that enables more diverse ...