406 citations · 2.5k across the 53 of their papers we have counts for
61 papers
Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
Shengjie Zhu, Abhinav Kumar, Masa Hu +1
3D sensing for monocular in-the-wild images, e.g., depth estimation and 3D object detection, has become increasingly important. However, the unknown intrinsic parameter hinders the…
PMatch: Paired Masked Image Modeling for Dense Geometric Matching
Shengjie Zhu, Xiaoming Liu
Dense geometric matching determines the dense pixel-wise correspondence between a source and support image corresponding to the same 3D structure. Prior works employ an encoder of…
Radar-Camera Pixel Depth Association for Depth Completion
Yunfei Long, Daniel Morris, Xiaoming Liu +3
While radar and video data can be readily fused at the detection level, fusing them at the pixel level is potentially more beneficial. This is also more challenging in part due to…
Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
Vishal Asnani, Xi Yin, Tal Hassner +1
State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. Identifying and understanding man…
Riggable 3D Face Reconstruction via In-Network Optimization
Ziqian Bai, Zhaopeng Cui, Xiaoming Liu +1
This paper presents a method for riggable 3D face reconstruction from monocular images, which jointly estimates a personalized face rig and per-image parameters including expressio…
Unified Detection of Digital and Physical Face Attacks
Debayan Deb, Xiaoming Liu, Anil K. Jain
State-of-the-art defense mechanisms against face attacks achieve near perfect accuracies within one of three attack categories, namely adversarial, digital manipulation, or physica…
Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
Feng Liu, Luan Tran, Xiaoming Liu
Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synth…
Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries
Saif Imran, Xiaoming Liu, Daniel Morris
Depth completion starts from a sparse set of known depth values and estimates the unknown depths for the remaining image pixels. Most methods model this as depth interpolation and…
Towards High Fidelity Face Relighting with Realistic Shadows
Andrew Hou, Ze Zhang, Michel Sarkis +3
Existing face relighting methods often struggle with two problems: maintaining the local facial details of the subject and accurately removing and synthesizing shadows in the relit…
GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
Abhinav Kumar, Garrick Brazil, Xiaoming Liu
Modern 3D object detectors have immensely benefited from the end-to-end learning idea. However, most of them use a post-processing algorithm called Non-Maximal Suppression (NMS) on…
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization
Xiaohong Liu, Yaojie Liu, Jun Chen +1
To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and loca…
Physics-Guided Spoof Trace Disentanglement for Generic Face Anti-Spoofing
Yaojie Liu, Xiaoming Liu
Prior studies show that the key to face anti-spoofing lies in the subtle image pattern, termed "spoof trace", e.g., color distortion, 3D mask edge, Moire pattern, and many others.…
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation
Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong +4
Standard registration algorithms need to be independently applied to each surface to register, following careful pre-processing and hand-tuning. Recently, learning-based approaches…
FaceGuard: A Self-Supervised Defense Against Adversarial Face Images
Debayan Deb, Xiaoming Liu, Anil K. Jain
Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial atta…
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
Feng Liu, Xiaoming Liu
The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner. Conventional implicit functions estimate the occupancy of a…
Kinematic 3D Object Detection in Monocular Video
Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu +1
Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and de…
On Disentangling Spoof Trace for Generic Face Anti-Spoofing
Yaojie Liu, Joel Stehouwer, Xiaoming Liu
Prior studies show that the key to face anti-spoofing lies in the subtle image pattern, termed "spoof trace", e.g., color distortion, 3D mask edge, Moire pattern, and many others.…
Mitigating Face Recognition Bias via Group Adaptive Classifier
Sixue Gong, Xiaoming Liu, Anil K. Jain
Face recognition is known to exhibit bias - subjects in a certain demographic group can be better recognized than other groups. This work aims to learn a fair face representation,…
LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
Abhinav Kumar, Tim K. Marks, Wenxuan Mou +6
Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted loca…
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
Yuge Huang, Yuhan Wang, Ying Tai +5
As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recent…
The Edge of Depth: Explicit Constraints between Segmentation and Depth
Shengjie Zhu, Garrick Brazil, Xiaoming Liu
In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsuperv…
Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
Joel Stehouwer, Amin Jourabloo, Yaojie Liu +1
Using printed photograph and replaying videos of biometric modalities, such as iris, fingerprint and face, are common attacks to fool the recognition systems for granting access as…
Camera Trace Erasing
Chang Chen, Zhiwei Xiong, Xiaoming Liu +1
Camera trace is a unique noise produced in digital imaging process. Most existing forensic methods analyze camera trace to identify image origins. In this paper, we address a new l…
Improving Face Recognition from Hard Samples via Distribution Distillation Loss
Yuge Huang, Pengcheng Shen, Ying Tai +5
Large facial variations are the main challenge in face recognition. To this end, previous variation-specific methods make full use of task-related prior to design special network l…