67 citations · 117 across the 13 of their papers we have counts for
13 papers
Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
Yifan Wang, Liya Ji, Zhanghan Ke +3
We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a…
Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks
Yuhao Liu, Zhanghan Ke, Fang Liu +2
Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle…
Recasting Regional Lighting for Shadow Removal
Yuhao Liu, Zhanghan Ke, Ke Xu +3
Removing shadows requires an understanding of both lighting conditions and object textures in a scene. Existing methods typically learn pixel-level color mappings between shadow an…
Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
Lei Zhu, Zhanghan Ke, Rynson Lau
Recent semi-supervised learning (SSL) methods typically include a filtering strategy to improve the quality of pseudo labels. However, these filtering strategies are usually hand-c…
Neural Preset for Color Style Transfer
Zhanghan Ke, Yuhao Liu, Lei Zhu +2
In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and sl…
BiFormer: Vision Transformer with Bi-Level Routing Attention
Lei Zhu, Xinjiang Wang, Zhanghan Ke +2
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation…
Structure-Informed Shadow Removal Networks
Yuhao Liu, Qing Guo, Lan Fu +5
Existing deep learning-based shadow removal methods still produce images with shadow remnants. These shadow remnants typically exist in homogeneous regions with low-intensity value…
Harmonizer: Learning to Perform White-Box Image and Video Harmonization
Zhanghan Ke, Chunyi Sun, Lei Zhu +2
Recent works on image harmonization solve the problem as a pixel-wise image translation task via large autoencoders. They have unsatisfactory performances and slow inference speeds…
MODNet-V: Improving Portrait Video Matting via Background Restoration
Jiayu Sun, Zhanghan Ke, Lihe Zhang +2
To address the challenging portrait video matting problem more precisely, existing works typically apply some matting priors that require additional user efforts to obtain, such as…
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
Zhanghan Ke, Jiayu Sun, Kaican Li +2
Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable…
Guided Collaborative Training for Pixel-wise Semi-Supervised Learning
Zhanghan Ke, Di Qiu, Kaican Li +2
We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the…
Towards Geometry Guided Neural Relighting with Flash Photography
Di Qiu, Jin Zeng, Zhanghan Ke +2
Previous image based relighting methods require capturing multiple images to acquire high frequency lighting effect under different lighting conditions, which needs nontrivial effo…
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
Zhanghan Ke, Daoye Wang, Qiong Yan +2
Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teache…