6 papers
Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video
Renlong Wu, Zhilu Zhang, Mingyang Chen +2
Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object…
Exposure Bracketing Is All You Need For A High-Quality Image
Zhilu Zhang, Shuohao Zhang, Renlong Wu +2
It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposur…
Retrieval Augmented Image Harmonization
Haolin Wang, Ming Liu, Zifei Yan +3
When embedding objects (foreground) into images (background), considering the influence of photography conditions like illumination, it is usually necessary to perform image harmon…
Learning Spatially Decoupled Color Representations for Facial Image Colorization
Hangyan Zhu, Ming Liu, Chao Zhou +3
Image colorization methods have shown prominent performance on natural images. However, since humans are more sensitive to faces, existing methods are insufficient to meet the dema…
Combining Generative and Geometry Priors for Wide-Angle Portrait Correction
Lan Yao, Chaofeng Chen, Xiaoming Li +2
Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially…
GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection
Hang Yao, Ming Liu, Haolin Wang +4
Diffusion models have shown superior performance on unsupervised anomaly detection tasks. Since trained with normal data only, diffusion models tend to reconstruct normal counterpa…