Computer Vision

Associated Publications

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Learning Object Permanence from Video
LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
UFO2: A Unified Framework towards Omni-supervised Object Detection
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera
Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies
Automated Synthetic-to-Real Generalization
Semi-Supervised StyleGAN for Disentanglement Learning
Angular Visual Hardness
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
Regularizing Neural Networks via Minimizing Hyperspherical Energy
Meshlet Priors for 3D Mesh Reconstruction
Bi3D: Stereo Depth Estimation via Binary Classifications
Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths
Self-Supervised Viewpoint Learning From Image Collections
Two-shot Spatially-varying BRDF and Shape Estimation
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views
Learning Canonical Representations for Scene Graph to Image Generation
DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
6-DOF Grasping for Target-driven Object Manipulation in Clutter
Toward Sim-to-Real Directional Semantic Grasping
Camera-to-Robot Pose Estimation from a Single Image
SymGAN: Orientation Estimation without Annotation for Symmetric Objects
NRMVS: Non-Rigid Multi-view Stereo
Neurreg: Neural registration and its application to image segmentation
Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation
Joint-task Self-supervised Learning for Temporal Correspondence
Dance to Music
Few-Shot Video-to-Video Synthesis
Joint Optimization for Cooperative Image Captioning
Content-Consistent Generation of Realistic Eyes with Style
Neural Inverse Rendering of an Indoor Scene from a Single Image
Few-Shot Adaptive Gaze Estimation
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data (ICCV 2019)
Neural Turtle Graphics for Modeling City Road Layouts
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
Meta-Sim: Learning to Generate Synthetic Datasets
6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
Extreme View Synthesis
SENSE: A Shared Encoder Network for Scene-flow Estimation
Confidence Regularized Self-Training
Few-Shot Unsupervised Image-to-Image Translation
Learning Propagation for Arbitrarily-Structured Data
Video Stitching for Linear Camera Arrays
Few-Shot Viewpoint Estimation
Semantic Image Synthesis with Spatially-Adaptive Normalization
Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition with Distractors
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
STEP: Spatio-Temporal Progressive Learning for Video Action Detection
Pixel-Adaptive Convolutional Neural Networks
Joint Discriminative and Generative Learning for Person Re-identification
SCOPS: Self-Supervised Co-Part Segmentation
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
Learning Linear Transformations for Fast Image and Video Style Transfer
Domain-Aware Generalized Zero-Shot Learning
Informative Object Annotations: Tell Me Something I Don't Know
Unsupervised Stylish Image Description Generation via Domain Layer Norm
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
A Fusion Approach for Multi-Frame Optical Flow Estimation
Localization-Aware Active Learning for Object Detection
Learning towards Minimum Hyperspherical Energy
Context-aware Synthesis and Placement of Object Instances
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Video-to-Video Synthesis
Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
Hand Pose Estimation via Latent 2.5 D Heatmap Regression
Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
Separating Reflection and Transmission Images in the Wild
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
Image Inpainting for Irregular Holes Using Partial Convolutions
HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration
Simultaneous Edge Alignment and Learning
Switchable Temporal Propagation Network
Multimodal Unsupervised Image-to-Image Translation
A Closed-form Solution to Photorealistic Image Stylization
EOE: Expected Overlap Estimation over Unstructured Point Cloud Data
3D MRI Brain Tumor Segmentation Using Autoencoder Regularization
Superpixel Sampling Networks
Noise2Noise: Learning Image Restoration without Clean Data
Light-weight Head Pose Invariant Gaze Tracking
MoCoGAN: Decomposing Motion and Content for Video Generation
Learning Superpixels with Segmentation-Aware Affinity Losse
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Improving Landmark Localization with Semi-Supervised Learning
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Decoupled Networks
Making Convolutional Networks Recurrent for Visual Sequence Learning
Deep Semantic Face Deblurring
Geometry-Aware Learning of Maps for Camera Localization
Learning Strict Identity Mappings in Deep Residual Networks
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations
Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
Reblur2Deblur: Deblurring Videos via Self-Supervised Learning
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach
Sim-to-Real Transfer of Accurate Grasping with Eye-In-Hand Observations and Continuous Control
On Nearest Neighbors in Non Local Means Denoising
Learning Affinity via Spatial Propagation Networks
Unsupervised Image-to-Image Translation Networks
Learning to Super-Resolve Blurry Face and Text Images
Semantic Video CNNs through Representation Warping
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
A Lightweight Approach for On-the-Fly Reflectance Estimation
Cascaded Scene Flow Prediction using Semantic Segmentation
Multiframe Scene Flow with Piecewise Rigid Motion
Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awareness
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Networks
Deep 360 Pilot: Learning a Deep Agent for Piloting through 360 Sports Videos
Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks
Reconstructing Intensity Images from Binary Spatial Gradient Cameras
Computational Zoom: A Framework for Post-Capture Image Composition
Polarimetric Multi-view Stereo
Context-aware Captions from Context-agnostic Supervision
Learning From Noisy Large-Scale Datasets With Minimal Supervision
Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
Reflectance Modeling by Neural Texture Synthesis
Accelerated Generative Models for 3D Point Cloud Data
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks
Robust Model-based 3D Head Pose Estimation
MLMD: Maximum Likelihood Mixture Decoupling for Fast and Accurate Point Cloud Registration
Filtering Environment Illumination for Interactive Physically-Based Rendering in Mixed Reality
Hand Gesture Recognition with 3D Convolutional Neural Networks
Retrieving Gray-Level Information from a Binary Sensor and its Application to Gesture Detection
Camera Re-calibration after Zooming based on Sets of Conics
Adaptive Segmentation based on a Learned Quality Metric
DT-SLAM: Deferred Triangulation for Robust SLAM
Addressing System-Level Optimization with OpenVX Graphs
WYSIWYG Computational Photography via Viewfinder Editing
An Energy Efficient Time-sharing Pyramid Pipeline for Multi-resolution Computer Vision
Practical SVBRDF Capture in the Frequency Domain
Realtime Computer Vision with OpenCV
Detecting Regions of Interest in Dynamic Scenes with Camera Motions
Robust Stereo with Flash and No-flash Image Pairs
What Characterizes a Shadow Boundary under Sun and Sky?
Dynamic Hand Gesture Recognition
Gaussian Process Regression Flow for Analysis of Motion Trajectories
Point Set Registration: Coherent Point Drift