Search Results for author:
Found 78 papers, 29 papers with code
Eyeglasses 3D shape reconstruction from a single face image
A complete 3D face reconstruction requires to explicitly model the eyeglasses on the face, which is less investigated in the literature.
Learning Physical Dynamics for Object-centric Visual Prediction
The ability to model the underlying dynamics of visual scenes and reason about the future is central to human intelligence.
NeRF as Non-Distant Environment Emitter in Physics-based Inverse Rendering
While the environment map is commonly used as the lighting model in inverse rendering, we show that its distant lighting assumption leads to spatial invariant lighting, which can be an inaccurate approximation in real-world inverse rendering.
OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering
State estimation for legged robots is challenging due to their highly dynamic motion and limitations imposed by sensor accuracy.
Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metric
Face aging has received continuous research attention over the past two decades.
Ship Detection in SAR Images with Human-in-the-Loop
Employing the proposed framework, an annotated ship database of SAR images is constructed, and the iteration experiments conducted during the construction demonstrates the efficiency of the method, providing new perspectives and approaches for research in this domain.
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering
Experiments demonstrate that, with the flexible input of single or sparse multi-view videos, we reconstruct personalized high-fidelity blendshapes.
ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation
Compared to conventional state-of-the-art semantic segmentation algorithms by extensive experiments, CWSAM showcases enhanced performance with fewer computing resources, highlighting the potential of leveraging foundational models like SAM for specific downstream tasks in the SAR domain.
Learning Surface Scattering Parameters From SAR Images Using Differentiable Ray Tracing
Furthermore, a differentiable ray tracing (DRT) engine based on SAR images was constructed for CSVBSDF surface scattering parameter learning.
Reinforcement Learning for SAR View Angle Inversion with Differentiable SAR Renderer
The electromagnetic inverse problem has long been a research hotspot.
Relightable and Animatable Neural Avatars from Videos
To solve this ill-posed problem, we propose novel techniques to better model the geometry and shadow changes.
Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem.
High-Quality Facial Geometry and Appearance Capture at Home
Facial geometry and appearance capture have demonstrated tremendous success in 3D scanning real humans in studios.
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging.
Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture
We believe that the combination is complementary and able to solve the inherent difficulties of using one modality input, including occlusions, extreme lighting/texture, and out-of-view for visual mocap and global drifts for inertial mocap.
Ranked #1 on
3D Human Pose Estimation
on AIST++
SAR-NeRF: Neural Radiance Fields for Synthetic Aperture Radar Multi-View Representation
SAR images are highly sensitive to observation configurations, and they exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features.
Physics-assisted Deep Learning for FMCW Radar Quantitative Imaging of Two-dimension Target
Radar imaging is crucial in remote sensing and has many applications in detection and autonomous driving.
Quantum-Enhanced Diamond Molecular Tension Microscopy for Quantifying Cellular Forces
The constant interplay and information exchange between cells and their micro-environment are essential to their survival and ability to execute biological functions.
Conceptual Study and Performance Analysis of Tandem Dual-Antenna Spaceborne SAR Interferometry
In this article, a new concept of Tandem Dual-Antenna SAR Interferometry (TDA-InSAR) system for single-pass reliable 3D surface mapping using the asymptotic 3D PU is proposed.
GFDC: A Granule Fusion Density-Based Clustering with Evidential Reasoning
Further, three novel granule fusion strategies are utilized to combine granules into stable cluster structures, helping to detect clusters with arbitrary shapes.
Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review
For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue to formulate a precise treatment plan.
EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors
We integrate the two techniques together in EgoLocate, a system that simultaneously performs human motion capture (mocap), localization, and mapping in real time from sparse body-mounted sensors, including 6 inertial measurement units (IMUs) and a monocular phone camera.
Hybrid RIS-Assisted MIMO Dual-Function Radar-Communication System
Dual-function radar-communication (DFRC) technology is emerging in next-generation wireless systems.
Learning a 3D Morphable Face Reflectance Model from Low-cost Data
This paper proposes the first 3D morphable face reflectance model with spatially varying BRDF using only low-cost publicly-available data.
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
In this paper, we propose a novel active imitation learning framework based on a teacher-student interaction model, in which the teacher's goal is to identify the best teaching behavior and actively affect the student's learning process.
EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
To achieve this, we propose a scene analysis method to detect and initialize key points by considering the dynamics in the scene, and a weighted key points strategy to model topologically varying dynamics by joint key points and weights optimization.
ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision
By supervising shadow rays, we successfully reconstruct a neural SDF of the scene from single-view images under multiple lighting conditions.
A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
Deep neural networks (DNNs), are widely used in many industries such as image recognition, supply chain, medical diagnosis, and autonomous driving.
Physical Interaction: Reconstructing Hand-object Interactions with Physics
Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions.
Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filter
Achieving highly accurate dynamic or simulator models that are close to the real robot can facilitate model-based controls (e. g., model predictive control or linear-quadradic regulators), model-based trajectory planning (e. g., trajectory optimization), and decrease the amount of learning time necessary for reinforcement learning methods.
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons.
The feasibility of Q-band millimeter wave on hand-gesture recognition for indoor FTTR scenario
The generalization for different scenarios and dif-ferent users is an urgent problem for millimeter wave gesture recognition for indoor fiber-to-the-room (FTTR) scenario.
Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation
Previous works on morphable models mostly focus on large-scale facial geometry but ignore facial details.
Self-Supervised Music-Motion Synchronization Learning for Music-Driven Conducting Motion Generation
Therefore, we propose a novel Music Motion Synchronized Generative Adversarial Network (M2S-GAN), which generates motions according to the automatically learned music representations.
Linear Leaky-Integrate-and-Fire Neuron Model Based Spiking Neural Networks and Its Mapping Relationship to Deep Neural Networks
Spiking neural networks (SNNs) are brain-inspired machine learning algorithms with merits such as biological plausibility and unsupervised learning capability.
EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model
Although significant progress has been made to audio-driven talking face generation, existing methods either neglect facial emotion or cannot be applied to arbitrary subjects.
Differentiable SAR Renderer and SAR Target Reconstruction
A 3D inverse target reconstruction algorithm from SAR images is devised.
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix
The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer.
Ranked #1 on
Image-to-Image Translation
on BCI
Breast Cancer Detection
Classification Of Breast Cancer Histology Images
+4
Detecting Topology Attacks against Graph Neural Networks
In this work, we study the victim node detection problem under topology attacks against GNNs.
Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data
In this paper, we propose a novel framework to remove eyeglasses as well as their cast shadows from face images.
OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction
In our technique, the motion of visible regions is first estimated and combined with temporal information to infer the motion of the occluded regions through an LSTM-involved graph neural network.
Data-Driven Robust Control for Discrete Linear Time-Invariant Systems: A Descriptor System Approach
Given the recent surge of interest in data-driven control, this paper proposes a two-step method to study robust data-driven control for a parameter-unknown linear time-invariant (LTI) system that is affected by energy-bounded noises.
Data-Driven Controllability Analysis and Stabilization for Linear Descriptor Systems
For a parameter-unknown linear descriptor system, this paper proposes data-driven methods to testify the system's type and controllability and then to stabilize it.
Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning
Experiments on MuJoCo and Hand Manipulation Suite tasks show that the agents deployed with our method achieve similar performance as it has in the source domain, while those deployed with previous methods designed for same-modal domain adaptation suffer a larger performance gap.
Backdoor Attack through Frequency Domain
We also evaluate FTROJAN against state-of-the-art defenses as well as several adaptive defenses that are designed on the frequency domain.
VirtualConductor: Music-driven Conducting Video Generation System
In this demo, we present VirtualConductor, a system that can generate conducting video from any given music and a single user's image.
Regret Minimization Experience Replay in Off-Policy Reinforcement Learning
In reinforcement learning, experience replay stores past samples for further reuse.
TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors
For global translation estimation, we propose a supporting-foot-based method and an RNN-based method to robustly solve for the global translations with a confidence-based fusion technique.
m6 A-related lncRNAs are potential biomarkers for predicting prognoses and immune responses in patients with LUAD
This risk model based on the m6 A-based lncRNAs may be promising for the clinical prediction of prognoses and immunotherapeutic responses in LUAD patients.
Audio-Driven Emotional Video Portraits
In this work, we present Emotional Video Portraits (EVP), a system for synthesizing high-quality video portraits with vivid emotional dynamics driven by audios.
Two-Dimensional DOA Estimation for L-shaped Nested Array via Tensor Modeling
To develop such approach, a higher-order tensor is constructed, whose factor matrices contain the sources azimuth and elevation information.
Transmit Beamspace DDMA Based Automotive MIMO Radar
The time division multiple access (TDMA) technique has been applied in automotive multiple-input multiple-output (MIMO) radar.
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15, 000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M.
DOA Estimation for Transmit Beamspace MIMO Radar via Tensor Decomposition with Vandermonde Factor Matrix
A computationally efficient tensor decomposition method is proposed to decompose the Vandermonde factor matrices.
Information Theory Signal Processing Information Theory
Cross-Modal Domain Adaptation for Reinforcement Learning
Domain adaptation is a promising direction for deploying RL agents in real-world applications, where vision-based robotics tasks constitute an important part.
Monocular Real-time Full Body Capture with Inter-part Correlations
We present the first method for real-time full body capture that estimates shape and motion of body and hands together with a dynamic 3D face model from a single color image.
Ranked #11 on
3D Hand Pose Estimation
on FreiHAND
Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering
Collaborative filtering has been widely used in recommender systems.
Joint DOD and DOA Estimation in Slow-Time MIMO Radar via PARAFAC Decomposition
We develop a new tensor model for slow-time multiple-input multiple output (MIMO) radar and apply it for joint direction-of-departure (DOD) and direction-of-arrival (DOA) estimation.
Deep Learning Meets SAR
Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data.
Deep Learning Based Single Sample Per Person Face Recognition: A Survey
Face recognition under this situation is referred to as single sample face recognition and poses significant challenges to the effective training of deep models.
Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data
We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy.
SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks
This paper aims to address this scalability challenge with a robust, sample-efficient, and general meta-IRL algorithm, SQUIRL, that performs a new but related long-horizon task robustly given only a single video demonstration.
Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
In this paper, we investigate a novel problem of telling the difference between image pairs in natural language.
A Closed-form Solution to Universal Style Transfer
Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.
DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs.
Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks
This paper attempts to develop machine intelligence that are trainable with large-volume co-registered SAR and optical images to translate SAR image to optical version for assisted SAR image interpretation.
Translating SAR to Optical Images for Assisted Interpretation
This paper attempts to develop machine intelligence that are trainable with large-volume co-registered SAR and optical images to translate SAR image to optical version for assisted SAR interpretation.
Real-time Indoor Scene Reconstruction with RGBD and Inertia Input
Experiments show that our patch deformation method improves the accuracy of feature tracking, and our 3D reconstruction outperforms the state-of-the-art solutions under fast camera motions.
DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs
Consumer depth sensors are more and more popular and come to our daily lives marked by its recent integration in the latest Iphone X.
Detecting Tiny Moving Vehicles in Satellite Videos
Even worse, the noise signals also existed in the video frames, since the background of the video frame has the subpixel-level and uneven moving thanks to the motion of satellites.
Depth Assisted Full Resolution Network for Single Image-based View Synthesis
In this paper, we focus on a more challenging and ill-posed problem that is to synthesize novel viewpoints from one single input image.
Deep learning in remote sensing: a review
In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with.
Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Our method decomposes the semantic style transfer problem into feature reconstruction part and feature decoder part.
BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera
To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method.
SAR Image Colorization: Converting Single-Polarization to Fully Polarimetric Using Deep Neural Networks
Both qualitative and quantitative experiments with real fully polarimetric data are conducted to show the efficacy of the proposed method.
Robust Non-Rigid Motion Tracking and Surface Reconstruction Using L0 Regularization
We present a new motion tracking method to robustly reconstruct non-rigid geometries and motions from single view depth inputs captured by a consumer depth sensor.
Want a Good Answer? Ask a Good Question First!
Community Question Answering (CQA) websites have become valuable repositories which host a massive volume of human knowledge.
