9 citations · 46 across the 41 of their papers we have counts for
7 papers · 1 filter
UniGS: Unified Representation for Image Generation and Segmentation
Lu Qi, Lehan Yang, Weidong Guo +4
This paper introduces a novel unified representation of diffusion models for image generation and segmentation. Specifically, we use a colormap to represent entity-level masks, add…
Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
Jiangning Zhang, Xuhai Chen, Yabiao Wang +5
This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultan…
Effective Adapter for Face Recognition in the Wild
Yunhao Liu, Yu-Ju Tsai, Kelvin C. K. Chan +3
In this paper, we tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions. Traditional heuristic approaches-eith…
Multi-task Image Restoration Guided By Robust DINO Features
Xin Lin, Jingtong Yue, Kelvin C. K. Chan +4
Multi-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. However, performance decline is…
Rethinking Evaluation Metrics of Open-Vocabulary Segmentaion
Hao Zhou, Tiancheng Shen, Xu Yang +4
In this paper, we highlight a problem of evaluation metrics adopted in the open-vocabulary segmentation. That is, the evaluation process still heavily relies on closed-set metrics…
Pyramid Diffusion for Fine 3D Large Scene Generation
Yuheng Liu, Xinke Li, Xueting Li +3
Diffusion models have shown remarkable results in generating 2D images and small-scale 3D objects. However, their application to the synthesis of large-scale 3D scenes has been rar…
Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark
Xin Lin, Jingtong Yue, Sixian Ding +3
Rain in the dark poses a significant challenge to deploying real-world applications such as autonomous driving, surveillance systems, and night photography. Existing low-light enha…