Chenyang Ge
YOU?
Author Swipe
View article: A Lightweight Model for Perceptual Image Compression via Implicit Priors
A Lightweight Model for Perceptual Image Compression via Implicit Priors Open
Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve…
View article: RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion
RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion Open
Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fideli…
View article: Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior
Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior Open
Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the p…
View article: Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey
Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey Open
This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we…
View article: Traditional Transformation Theory Guided Model for Learned Image Compression
Traditional Transformation Theory Guided Model for Learned Image Compression Open
Recently, many deep image compression methods have been proposed and achieved remarkable performance. However, these methods are dedicated to optimizing the compression performance and speed at medium and high bitrates, while research on u…
View article: Real‐world image deblurring using data synthesis and feature complementary network
Real‐world image deblurring using data synthesis and feature complementary network Open
Many learning‐based approaches to image deblurring have received increasing attention in recent years. However, the models trained on existing synthetic datasets do not generalize well to real‐world blur, resulting in undesirable artifacts…
View article: Depth Super-Resolution from Explicit and Implicit High-Frequency Features
Depth Super-Resolution from Explicit and Implicit High-Frequency Features Open
We propose a novel multi-stage depth super-resolution network, which progressively reconstructs high-resolution depth maps from explicit and implicit high-frequency features. The former are extracted by an efficient transformer processing …
View article: Rethinking Blur Synthesis for Deep Real-World Image Deblurring
Rethinking Blur Synthesis for Deep Real-World Image Deblurring Open
In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design. D…
View article: Depth Restoration in Under-Display Time-of-Flight Imaging
Depth Restoration in Under-Display Time-of-Flight Imaging Open
Under-display imaging has recently received considerable attention in both academia and industry. As a variation of this technique, under-display ToF (UD-ToF) cameras enable depth sensing for full-screen devices. However, it also brings pr…
View article: A High Spatial Resolution Depth Sensing Method Based on Binocular Structured Light
A High Spatial Resolution Depth Sensing Method Based on Binocular Structured Light Open
Depth information has been used in many fields because of its low cost and easy availability, since the Microsoft Kinect was released. However, the Kinect and Kinect-like RGB-D sensors show limited performance in certain applications and p…