94 citations · 100 across the 26 of their papers we have counts for
26 papers
ASTRA-SR: Atmospheric Seeing and Turbulence Restoration for Astronomical Image Super-Resolution
Xining Ge, Ziteng Cui, Shuhong Liu
Ground-based planetary imaging suffers from atmospheric turbulence, sensor noise, and limited sampling, making restoration a joint denoising, deblurring, and super-resolution probl…
FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting
Gengjia Chang, Ziteng Cui, Shuhong Liu
The appearance of a smoky scene is shaped by two processes that a camera records together: the participating medium alters scene radiance in a view-dependent way, and the image sig…
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
Heng Zhou, Shuhong Liu, Yonghao He +6
We present X-lens, a compact feed-forward model for metric depth estimation from a variable number of calibrated fisheye and pinhole views. To support real-time downstream percepti…
CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation
Xuangeng Chu, Yuan Gan, Ziteng Cui +4
Audio-driven 3D facial animation aims to generate synchronized lip movements and vivid facial expressions from arbitrary audio clips. While existing methods can produce synchronize…
RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
Shuhong Liu, Gengjia Chang, Jun Liu +4
Camera sensor RAW data offers intrinsic advantages for object detection, including deeper bit depth, preserved physical information, and freedom from image signal processor (ISP) d…
FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
Shuhong Liu, Xining Ge, Ziteng Cui +8
Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution a…
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
Shuhong Liu, Chenyu Bao, Ziteng Cui +103
This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to…
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Liuzhuozheng Li, Zhiyuan Zhan, Shuhong Liu +5
Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic method…
Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
Gengjia Chang, Xining Ge, Weijun Yuan +4
Single-image super-resolution has progressed from deep convolutional baselines to stronger Transformer and state-space architectures, yet the corresponding performance gains typica…
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
Gengjia Chang, Xining Ge, Weijun Yuan +4
This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level ). Rather than proposing a new restoration…
Dual-Branch Remote Sensing Infrared Image Super-Resolution
Xining Ge, Gengjia Chang, Weijun Yuan +6
Remote sensing infrared image super-resolution aims to recover sharper thermal observations from low-resolution inputs while preserving target contours, scene layout, and radiometr…
CLIP-Guided Data Augmentation for Night-Time Image Dehazing
Xining Ge, Weijun Yuan, Gengjia Chang +2
Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, non-uniform lighting, and strong l…
The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report
Bin Ren, Hang Guo, Yan Shu +60
This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a…
Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis
Ziteng Cui, Shuhong Liu, Xiaoyu Dong +4
High-quality image acquisition in real-world environments remains challenging due to complex illumination variations and inherent limitations of camera imaging pipelines. These iss…
POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
Yi Chen, Wonjin Shin, Shuhong Liu +6
Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during inference, overlooking spars…
RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction
Shuhong Liu, Chenyu Bao, Ziteng Cui +11
We introduce RealX3D, a real-capture benchmark for multi-view visual restoration and 3D reconstruction under diverse physical degradations. RealX3D groups corruptions into four fam…
Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
Shuhong Liu, Xining Ge, Ziying Gu +7
Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts but largely leave stochastic noise unres…
I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
Shuhong Liu, Lin Gu, Ziteng Cui +2
Participating in efforts to endow generative AI with the 3D physical world perception, we propose I2-NeRF, a novel neural radiance field framework that enhances isometric and isotr…
DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments
Shuhong Liu, Xiang Chen, Hongming Chen +2
Reconstruction under adverse rainy conditions poses significant challenges due to reduced visibility and the distortion of visual perception. These conditions can severely impair t…
Gradient-based optimization of spintronic devices
Yusuke Imai, Shuhong Liu, Nozomi Akashi +1
The optimization of physical parameters serves various purposes, such as system identification and efficiency in developing devices. Spin-torque oscillators have been applied to ne…
Exploiting Chaotic Dynamics as Deep Neural Networks
Shuhong Liu, Nozomi Akashi, Qingyao Huang +2
Chaos presents complex dynamics arising from nonlinearity and a sensitivity to initial states. These characteristics suggest a depth of expressivity that underscores their potentia…
Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge
Tianchen Deng, Yi Zhou, Wenhua Wu +9
This technical report presents the 1st winning model for UG2+, a task in CVPR 2024 UAV Tracking and Pose-Estimation Challenge. This challenge faces difficulties in drone detection,…
NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
Jingwei Huang, Mingrui Li, Lei Sun +3
SLAM systems based on Gaussian Splatting have garnered attention due to their capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatt…
MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction
Heng Zhou, Zhetao Guo, Shuhong Liu +4
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for…