Optical computing has emerged as a powerful approach for high-speed and energy-efficient information processing. Diffractive ...

A new study presents a zero-shot learning (ZSL) framework for maize cob phenotyping, enabling the extraction of geometric ...

SVG Autoencoder - Uses a frozen representation encoder with a residual branch to compensate the information loss and a learned convolutional decoder to transfer the SVG latent space to pixel space.

Abstract: Removing noise from infrared images is of great significance in various fields. The existing infrared image denoising methods have the problem of an imbalance between noise suppression and ...

Abstract: Low-light image enhancement aims to improve the visibility and the contrast of images captured under poor lighting conditions while preserving contextual details. In this context, most ...

This repository presents Reinforcement Learning Guidance (RLG), an innovative inference-time method designed to enhance and control the alignment of diffusion models. RLG builds upon the widely used ...