7 papers · 2 filters
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Kendong Liu, Zhiyu Zhu, Chuanhao Li +3
In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improvi…
Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation
Bo Han, Yuheng Jia, Hui Liu +1
Spectral variations pose a common challenge in analyzing hyperspectral images (HSI). To address this, low-rank tensor representation has emerged as a robust strategy, leveraging in…
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
Zhiyu Zhu, Jinhui Hou, Hui Liu +2
The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e.g., low-quality im…
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
Meng You, Zhiyu Zhu, Hui Liu +1
By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit…
RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering
Xianqiang Lyu, Hui Liu, Junhui Hou
We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural ren…
Towards Calibrated Deep Clustering Network
Yuheng Jia, Jianhong Cheng, Hui Liu +1
Deep clustering has exhibited remarkable performance; however, the over confidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly ex…
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
Jianhan Qi, Yuheng Jia, Hui Liu +1
Hyperspectral images (HSI) clustering is an important but challenging task. The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the…