Picture for Jingyu Yang

Jingyu Yang

MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results

Apr 30, 2024
Viaarxiv icon

LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging

Apr 08, 2024
Viaarxiv icon

DeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable Diffusion

Add code
Mar 31, 2024
Viaarxiv icon

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors

Add code
Mar 07, 2024
Figure 1 for AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Figure 2 for AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Figure 3 for AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Figure 4 for AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Viaarxiv icon

A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection

Add code
Feb 29, 2024
Viaarxiv icon

KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matching

Add code
Jan 02, 2024
Viaarxiv icon

Learning to See Low-Light Images via Feature Domain Adaptation

Dec 20, 2023
Figure 1 for Learning to See Low-Light Images via Feature Domain Adaptation
Figure 2 for Learning to See Low-Light Images via Feature Domain Adaptation
Figure 3 for Learning to See Low-Light Images via Feature Domain Adaptation
Figure 4 for Learning to See Low-Light Images via Feature Domain Adaptation
Viaarxiv icon

MARIS: Referring Image Segmentation via Mutual-Aware Attention Features

Add code
Nov 27, 2023
Figure 1 for MARIS: Referring Image Segmentation via Mutual-Aware Attention Features
Figure 2 for MARIS: Referring Image Segmentation via Mutual-Aware Attention Features
Figure 3 for MARIS: Referring Image Segmentation via Mutual-Aware Attention Features
Figure 4 for MARIS: Referring Image Segmentation via Mutual-Aware Attention Features
Viaarxiv icon

High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videos

Nov 02, 2023
Viaarxiv icon

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

Add code
Oct 31, 2023
Viaarxiv icon