Search Results for author: Feng Lu

Found 52 papers, 14 papers with code

CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis

no code implementations ECCV 2020 Jiadong Liang, Wenjie Pei, Feng Lu

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly.

Image Generation Semantic correspondence +1

PCFGaze: Physics-Consistent Feature for Appearance-based Gaze Estimation

no code implementations5 Sep 2023 Yiwei Bao, Feng Lu

Although recent deep learning based gaze estimation approaches have achieved much improvement, we still know little about how gaze features are connected to the physics of gaze.

Gaze Estimation

DVGaze: Dual-View Gaze Estimation

1 code implementation ICCV 2023 Yihua Cheng, Feng Lu

We further propose a dual-view transformer to estimate gaze from dual-view features.

Gaze Estimation

SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations

no code implementations17 Aug 2023 Zhiming Wang, Lin Gu, Feng Lu

Our method also achieves an accuracy of 74. 84% on the task of recognizing low-resolution facial expressions, surpassing the current state-of-the-art FMD by 9. 48%.


Visibility Enhancement for Low-light Hazy Scenarios

no code implementations1 Aug 2023 Chaoqun Zhuang, Yunfei Liu, Sijia Wen, Feng Lu

The simulation is designed for generating the dataset with ground-truths by the proposed low-light hazy imaging model.

Image Dehazing SSIM

NPR: Nocturnal Place Recognition in Streets

no code implementations1 Apr 2023 Bingxi Liu, Yujie Fu, Feng Lu, Jinqiang Cui, Yihong Wu, Hong Zhang

Then we used this model to process existing large-scale VPR datasets to generate the VPR-Night datasets and demonstrated how to combine them with two popular VPR pipelines.

Image-to-Image Translation Visual Place Recognition

Jitter Does Matter: Adapting Gaze Estimation to New Domains

no code implementations5 Oct 2022 Ruicong Liu, Yiwei Bao, Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu

We evaluate the proposed method on four cross-domain gaze estimation tasks, and experimental results demonstrate that it significantly reduces the gaze jitter and improves the gaze estimation performance in target domains.

Adversarial Attack Contrastive Learning +2

Discriminative feature encoding for intrinsic image decomposition

no code implementations25 Sep 2022 Zongji Wang, Yunfei Liu, Feng Lu

Intrinsic image decomposition is an important and long-standing computer vision problem.

Intrinsic Image Decomposition

Layout-Bridging Text-to-Image Synthesis

no code implementations12 Aug 2022 Jiadong Liang, Wenjie Pei, Feng Lu

Specifically, we formulate the text-to-layout generation as a sequence-to-sequence modeling task, and build our model upon Transformer to learn the spatial relationships between objects by modeling the sequential dependencies between them.

Image Generation

Gaze-Vergence-Controlled See-Through Vision in Augmented Reality

no code implementations6 Jul 2022 Zhimin Wang, Yuxin Zhao, Feng Lu

This is because when we want to see through something, it is physically related to our gaze depth/vergence and thus should be naturally controlled by the eyes.

Depth Estimation

GazeOnce: Real-Time Multi-Person Gaze Estimation

no code implementations CVPR 2022 Mingfang Zhang, Yunfei Liu, Feng Lu

In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image.

Gaze Estimation

Cloud Sphere: A 3D Shape Representation via Progressive Deformation

no code implementations21 Dec 2021 Zongji Wang, Yunfei Liu, Feng Lu

In the area of 3D shape analysis, the geometric properties of a shape have long been studied.

3D Shape Representation

Separating Content and Style for Unsupervised Image-to-Image Translation

1 code implementation27 Oct 2021 Yunfei Liu, Haofei Wang, Yang Yue, Feng Lu

Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples.

Translation Unsupervised Image-To-Image Translation

Assessment of Deep Learning-based Heart Rate Estimation using Remote Photoplethysmography under Different Illuminations

no code implementations28 Jul 2021 Ze Yang, Haofei Wang, Feng Lu

We evaluate the performance of three deep learning-based methods (Deepphys, rPPGNet, and Physnet) to that of four traditional methods (CHROM, GREEN, ICA, and POS) using two public datasets: the UBFC-rPPG dataset and the BH-rPPG dataset.

Heart rate estimation POS

Explainable Diabetic Retinopathy Detection and Retinal Image Generation

1 code implementation1 Jul 2021 Yuhao Niu, Lin Gu, Yitian Zhao, Feng Lu

Though deep learning has shown successful performance in classifying the label and severity stage of certain diseases, most of them give few explanations on how to make predictions.

Data Augmentation Diabetic Retinopathy Detection +4

Gaze Estimation using Transformer

1 code implementation30 May 2021 Yihua Cheng, Feng Lu

In this paper, we employ transformers and assess their effectiveness for gaze estimation.

Gaze Estimation

Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark

7 code implementations26 Apr 2021 Yihua Cheng, Haofei Wang, Yiwei Bao, Feng Lu

However, it lacks a guideline for designing deep learning algorithms for gaze estimation tasks.

Gaze Estimation

STA-VPR: Spatio-temporal Alignment for Visual Place Recognition

1 code implementation25 Mar 2021 Feng Lu, Baifan Chen, Xiang-Dong Zhou, Dezhen Song

Here we split the holistic mid-layer features into local features, and propose an adaptive dynamic time warping (DTW) algorithm to align local features from the spatial domain while measuring the distance between two images.

Dynamic Time Warping Visual Place Recognition

Vulnerability of Appearance-based Gaze Estimation

no code implementations24 Mar 2021 Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu

However, many deep learning-based methods suffer from the vulnerability property, i. e., perturbing the raw image using noise confuses the gaze estimation models.

Adversarial Attack Gaze Estimation

PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation

1 code implementation24 Mar 2021 Yihua Cheng, Yiwei Bao, Feng Lu

Different from common domain adaption methods, we propose a domain generalization method to improve the cross-domain performance without touching target samples.

Domain Generalization Gaze Estimation

Polarization Guided Specular Reflection Separation

no code implementations22 Mar 2021 Sijia Wen, Yingqiang Zheng, Feng Lu

Based on the analysis of polarization, we propose a polarization guided model to generate a polarization chromaticity image, which is able to reveal the geometrical profile of the input image in complex scenarios, such as diversity of illumination.

Unsupervised Two-Stage Anomaly Detection

no code implementations22 Mar 2021 Yunfei Liu, Chaoqun Zhuang, Feng Lu

Anomaly detection from a single image is challenging since anomaly data is always rare and can be with highly unpredictable types.

Anomaly Detection Image Reconstruction +1

Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets

no code implementations20 Mar 2021 Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu

Meanwhile, we also propose Adaptive Group Normalization to recalibrate eye features with the guidance of facial feature.

Gaze Estimation

An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation

no code implementations10 Jan 2021 Maohan Liang, Ryan Wen Liu, Shichen Li, Zhe Xiao, Xin Liu, Feng Lu

Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner.

Clustering Trajectory Clustering

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

3 code implementations ECCV 2020 Yunfei Liu, Xingjun Ma, James Bailey, Feng Lu

A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data.

Backdoor Attack

Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

no code implementations31 May 2020 Feifan Lv, Bo Liu, Feng Lu

This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively.

Image Enhancement

An Integrated Enhancement Solution for 24-hour Colorful Imaging

no code implementations10 May 2020 Feifan Lv, Yinqiang Zheng, Yicheng Li, Feng Lu

The current industry practice for 24-hour outdoor imaging is to use a silicon camera supplemented with near-infrared (NIR) illumination.

Beyond Optimizing for Clicks: Incorporating Editorial Values in News Recommendation

no code implementations21 Apr 2020 Feng Lu, Anca Dumitrache, David Graus

In our first study we explore how our news recommender steers reading behavior in the context of editorial values such as serendipity, dynamism, diversity, and coverage.

News Recommendation Recommendation Systems +1

CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis

1 code implementation18 Dec 2019 Jiadong Liang, Wenjie Pei, Feng Lu

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly.

Image Generation Semantic correspondence +1

A Sparse Representation Based Joint Demosaicing Method for Single-Chip Polarized Color Sensor

no code implementations16 Dec 2019 Sijia Wen, Yinqiang Zheng, Feng Lu

Instead of mechanically demosaicing for the multi-channel polarized color image, we further present a sparse representation-based optimization strategy that utilizes chromatic information and polarimetric information to jointly optimize the model.


Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

2 code implementations CVPR 2020 Yunfei Liu, Yu Li, ShaoDi You, Feng Lu

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene.

Intrinsic Image Decomposition

Real-Time Semantic Segmentation via Multiply Spatial Fusion Network

no code implementations17 Nov 2019 Haiyang Si, Zhiqiang Zhang, Feifan Lv, Gang Yu, Feng Lu

Specifically, it achieves 77. 1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75. 4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.

Autonomous Driving Playing the Game of 2048 +1

Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset

3 code implementations2 Aug 2019 Feifan Lv, Yu Li, Feng Lu

Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark.

 Ranked #1 on Low-Light Image Enhancement on 3DMatch Benchmark (using extra training data)

Denoising Low-Light Image Enhancement

Semantic Guided Single Image Reflection Removal

1 code implementation27 Jul 2019 Yunfei Liu, Yu Li, ShaoDi You, Feng Lu

Reflection is common in images capturing scenes behind a glass window, which is not only a disturbance visually but also influence the performance of other computer vision algorithms.

Reflection Removal

Hyperspectral City V1.0 Dataset and Benchmark

no code implementations24 Jul 2019 Shaodi You, Erqi Huang, Shuaizhe Liang, Yongrong Zheng, Yunxiang Li, Fan Wang, Sen Lin, Qiu Shen, Xun Cao, Diming Zhang, Yuanjiang Li, Yu Li, Ying Fu, Boxin Shi, Feng Lu, Yinqiang Zheng, Robby T. Tan

This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.

Separate In Latent Space: Unsupervised Single Image Layer Separation

no code implementations3 Jun 2019 Yunfei Liu, Feng Lu

Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation.

Intrinsic Image Decomposition Reflection Removal

What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis

no code implementations16 Apr 2019 Huangyue Yu, Minjie Cai, Yunfei Liu, Feng Lu

However, techniques for analyzing the first-person video can be fundamentally different from those for the third-person video, and it is even more difficult to explore the shared information from both viewpoints.

Self-Supervised Learning

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

1 code implementation6 Dec 2018 Yuhao Niu, Lin Gu, Feng Lu, Feifan Lv, Zongji Wang, Imari Sato, Zijian Zhang, Yangyan Xiao, Xunzhang Dai, Tingting Cheng

Inspired by Koch's Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector.

Medical Diagnosis

Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks

no code implementations3 Sep 2018 Zhixiang Hao, Yu Li, ShaoDi You, Feng Lu

However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application.

Depth Estimation

VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes

no code implementations1 Sep 2018 Zongji Wang, Feng Lu

Voxel is an important format to represent geometric data, which has been widely used for 3D deep learning in shape analysis due to its generalization ability and regular data format.

Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression

no code implementations ECCV 2018 Yihua Cheng, Feng Lu, Xucong Zhang

Inspired by this, we design the multi-stream ARE-Net; one asymmetric regression network (AR-Net) predicts 3D gaze directions for both eyes with a novel asymmetric strategy, and the evaluation network (E-Net) adaptively adjusts the strategy by evaluating the two eyes in terms of their performance during optimization.

Gaze Estimation regression

Uncalibrated Photometric Stereo Under Natural Illumination

no code implementations CVPR 2018 Zhipeng Mo, Boxin Shi, Feng Lu, Sai-Kit Yeung, Yasuyuki Matsushita

This paper presents a photometric stereo method that works with unknown natural illuminations without any calibration object.

Look, Perceive and Segment: Finding the Salient Objects in Images via Two-Stream Fixation-Semantic CNNs

no code implementations ICCV 2017 Xiaowu Chen, Anlin Zheng, Jia Li, Feng Lu

Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by selecting the pre-segmented semantic objects that receive the highest fixation density in eye-tracking experiments.

object-detection RGB Salient Object Detection +1

Uncalibrated Photometric Stereo Based on Elevation Angle Recovery From BRDF Symmetry of Isotropic Materials

no code implementations CVPR 2015 Feng Lu, Imari Sato, Yoichi Sato

This sort of symmetry can be observed in a 1D BRDF slice from a subset of surface normals with the same azimuth angle, and we use it to devise an efficient modeling and solution method to constrain and recover the elevation angles of surface normals accurately.

A New Way to Factorize Linear Cameras

no code implementations22 Dec 2014 Feng Lu, Ziqiang Chen

The implementation details of factorizing the 3x4 projection matrices of linear cameras into their left matrix factors and the 4x4 homogeneous central(also parallel for infinite center cases) projection factors are presented in this work.

A General Homogeneous Matrix Formulation to 3D Rotation Geometric Transformations

no code implementations24 Apr 2014 Feng Lu, Ziqiang Chen

We present algebraic projective geometry definitions of 3D rotations so as to bridge a small gap between the applications and the definitions of 3D rotations in homogeneous matrix form.

Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances

no code implementations CVPR 2013 Feng Lu, Yasuyuki Matsushita, Imari Sato, Takahiro Okabe, Yoichi Sato

We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances.

Cannot find the paper you are looking for? You can Submit a new open access paper.