62 citations · 191 across the 25 of their papers we have counts for
25 papers
Joint Depth Estimation and Mixture of Rain Removal From a Single Image
Yongzhen Wang, Xuefeng Yan, Yanbiao Niu +3
Rainy weather significantly deteriorates the visibility of scene objects, particularly when images are captured through outdoor camera lenses or windshields. Through careful observ…
Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction
Jiayang Bai, Zhen He, Shan Yang +4
Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robu…
Self-NeRF: A Self-Training Pipeline for Few-Shot Neural Radiance Fields
Jiayang Bai, Letian Huang, Wen Gong +2
Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued…
Deep Point Cloud Simplification for High-quality Surface Reconstruction
Yuanqi Li, Jianwei Guo, Xinran Yang +4
The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying…
Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction
Jiayang Bai, Jie Guo, Chenchen Wan +6
Lighting prediction from a single image is becoming increasingly important in many vision and augmented reality (AR) applications in which shading and shadow consistency between vi…
GLPanoDepth: Global-to-Local Panoramic Depth Estimation
Jiayang Bai, Shuichang Lai, Haoyu Qin +2
In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image. An omnidirectional image has a full field-of-…
Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation
Yang Zhang, Yang Yang, Chenyun Xiong +2
Encoder-decoder models have been widely used in RGBD semantic segmentation, and most of them are designed via a two-stream network. In general, jointly reasoning the color and geom…
GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection
C. Zheng, D. Shi, X. Yan +5
Most of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects be…
A Transductive Maximum Margin Classifier for Few-Shot Learning
Fei Pan, Chunlei Xu, Jie Guo +1
Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled examples per class are given. We introduce a transductive maximum margin c…
Temporal Alignment Prediction for Few-Shot Video Classification
Fei Pan, Chunlei Xu, Jie Guo +1
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult…
Rendering Discrete Participating Media with Geometrical Optics Approximation
Jie Guo, Bingyang Hu, Yanjun Chen +3
We consider the scattering of light in participating media composed of sparsely and randomly distributed discrete particles. The particle size is expected to range from the scale o…
A Unified Light Framework for Real-time Fault Detection of Freight Train Images
Yang Zhang, Moyun Liu, Yang Yang +2
Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements.…
Tensor Composition Net for Visual Relationship Prediction
Yuting Qiang, Yongxin Yang, Xueting Zhang +2
We present a novel Tensor Composition Net (TCN) to predict visual relationships in images. Visual Relationship Prediction (VRP) provides a more challenging test of image understand…
Hierarchical Context Embedding for Region-based Object Detection
Zhao-Min Chen, Xin Jin, Borui Zhao +2
State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The…
Image Stitching Based on Planar Region Consensus
Aocheng Li, Jie Guo, Yanwen Guo
Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of planar structure under perspective g…
FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces
Jingwu He, Chuan Wang, Yang Zhang +2
Facial attractiveness enhancement has been an interesting application in Computer Vision and Graphics over these years. It aims to generate a more attractive face via manipulations…
Affinity Fusion Graph-based Framework for Natural Image Segmentation
Yang Zhang, Moyun Liu, Jingwu He +2
This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The…
Hybrid Models for Open Set Recognition
Hongjie Zhang, Ang Li, Jie Guo +1
Open set recognition requires a classifier to detect samples not belonging to any of the classes in its training set. Existing methods fit a probability distribution to the trainin…
Multi-Label Image Recognition with Graph Convolutional Networks
Zhao-Min Chen, Xiu-Shen Wei, Peng Wang +1
The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the labe…
Viewpoint Selection for Photographing Architectures
Jingwu He, Linbo Wang, Wenzhe Zhou +3
This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous l…
A Data-driven Approach for Furniture and Indoor Scene Colorization
Jie Zhu, Yanwen Guo, Han Ma
We present a data-driven approach that colorizes 3D furniture models and indoor scenes by leveraging indoor images on the internet. Our approach is able to colorize the furniture a…
Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models
Yu-ting Qiang, Yanwei Fu, Xiao Yu +3
Researchers often summarize their work in the form of scientific posters. Posters provide a coherent and efficient way to convey core ideas expressed in scientific papers. Generati…
Learning to Generate Posters of Scientific Papers
Yuting Qiang, Yanwei Fu, Yanwen Guo +2
Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientifi…
Efficient Discriminative Nonorthogonal Binary Subspace with its Application to Visual Tracking
Ang Li, Feng Tang, Yanwen Guo +1
One of the crucial problems in visual tracking is how the object is represented. Conventional appearance-based trackers are using increasingly more complex features in order to be…