13 papers
From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance
Long Cao, Zhongquan Wang, Jie Li +4
Image priors can synthesize target conditions for 3D Gaussian street scenes, but independently edited views do not define a coherent 3D target. Direct fitting can propagate view-sp…
AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement
Yuhan Chen, Kunyang Huang, Fuchen Li +4
Existing low-light image enhancement methods often face a bottleneck between the representation capacity of illumination-field modeling and computational complexity. To address thi…
Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement
Yuhan Chen, Wenxuan Yu, Guofa Li +6
Existing unsupervised low-light image enhancement methods often encounter local exposure imbalance and color distortion under complex non-uniform illumination. In addition, most Vi…
Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing
Yuhan Chen, Ying Fang, Guofa Li +5
Single image dehazing continues to be hindered by the loss of high-frequency details and the difficulty of accurate physical scattering modeling. To address these issues, we propos…
Dehaze-GaussianImage: Zero-Shot Dehazing via Efficient 2D Gaussian Splatting Representation
Yuhan Chen, Wenxuan Yu, Guofa Li +5
Existing single image dehazing methods are often constrained by computational redundancy in pixel-level optimization and the lack of physical interpretability in implicit neural ne…
Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement
Yuhan Chen, Yicui Shi, Guofa Li +5
Low-light image enhancement aims to recover clear images from low-illumination observations and is crucial for high-level downstream vision tasks. However, existing methods frequen…
KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition
Yuhan Chen, Yicui Shi, Guofa Li +4
Skeleton-based action recognition is widely applied in sensor-based systems, including human-computer interaction and intelligent surveillance. However, typical sensors produce spa…
LL-GaussianMap: Zero-shot Low-Light Image Enhancement via 2D Gaussian Splatting Guided Gain Maps
Yuhan Chen, Ying Fang, Guofa Li +6
Significant progress has been made in low-light image enhancement with respect to visual quality. However, most existing methods primarily operate in the pixel domain or rely on im…
LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting
Yuhan Chen, Wenxuan Yu, Guofa Li +6
2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios.…
Shift-Window Meets Dual Attention: A Multi-Model Architecture for Specular Highlight Removal
Tianci Huo, Lingfeng Qi, Yuhan Chen +6
Inevitable specular highlights in practical environments severely impair the visual performance, thus degrading the task effectiveness and efficiency. Although there exist consider…
UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement
Yuhan Chen, Yicui Shi, Guofa Li +5
Addressing the urgent need for high-performance real-time low-light image enhancement on resource-constrained edge devices in low-illumination scenarios such as nighttime and tunne…
PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting
Yijun Xu, Jingrui Zhang, Hongyi Liu +6
Reconstruction of rigid motion over large spatiotemporal scales remains a challenging task due to limitations in modeling paradigms, severe motion blur, and insufficient physical c…
Hybrid Event Frame Sensors: Modeling, Calibration, and Simulation
Yunfan Lu, Nico Messikommer, Xiaogang Xu +5
Hybrid event-frame sensors integrate an Event Vision Sensor (EVS) and an Active Pixel Sensor (APS) within a single chip, combining the high dynamic range and low latency of the EVS…