Program
Presenter instructions: If you are a presenter (oral or poster session) check here the instructions.
Keynote Speakers
Conference Program Overview
Monday, 10/9/2017 | |
---|---|
10:00 AM - 6:00 PM | Register |
Tuesday, 10/10/2017 | |
9:00 - 9:15 AM | Opening Remarks |
9:15 - 10:00 AM | Keynote 1: Zhengyou Zhang, "3D Computer Vision for Immersive Interaction and Remote Collaboration" |
10:00 - 10:30 AM | Coffee Break |
10:30 - 11:10 AM | Oral Session 1 |
11:10 - 11:30 AM | Spotlight Session 1 |
11:30 - 12:30 PM | Poster session 1 |
12:30 - 2:00 PM | Lunch |
2:00 - 2:45 PM | Keynote 2: Davide Scaramuzza,"Robust, Visual-Inertial State Estimation: from Frame-based to Event-based Cameras" |
2:45 - 3:10 PM | Coffee Break |
3:10 - 3:50 PM | Oral Session 2 |
3:50 - 5:20 PM | Forum: The challenges and opportunities in 3D sensing |
5:20 - 6:20 PM | Poster session 1 |
6:20 - 8:20 PM | Welcome Reception |
Wednesday, 10/11/2017 | |
---|---|
9:00 - 9:15 AM | Announcements |
9:15 - 10:00 AM | Keynote 3: Wen Gao, "Online visual processing for 3D reconstruction, SLAM, and object recognition" |
10:00 - 10:30 AM | Coffee Break |
10:30 - 11:10 AM | Oral Session 3 |
11:10 - 11:30 AM | Spotlight Session 2 |
11:30 - 12:30 PM | Poster session 2 |
12:30 - 2:00 PM | Lunch |
2:00 - 2:45 PM | Keynote 4: Long Quan, "Computer Vision, Visual Learning, and 3D Reconstruction: Modeling the world with drones and smartphones!" |
2:45 - 3:10 PM | Coffee Break |
3:10 - 3:50 PM | Oral Session 4 |
3:50 - 4:25 PM | Spotlight Session 3 |
4:25 - 5:25 PM | Poster session 2 |
5:30 - 8:00 PM | Banquet |
Thursday, 10/12/2017 | |
---|---|
9:00 - 9:15 AM | Announcements |
9:15 - 10:00 AM | Keynote 5: Niloy Mitra, "Building a Factorized Scene Model: Capturing Appearance, Geometry, and Interactions" |
10:00 - 10:30 AM | Coffee Break |
10:30 - 11:10 AM | Oral Session 5 |
11:10 - 11:30 AM | Spotlight Session 4 |
11:30 - 12:30 PM | Poster session 3 |
12:30 - 2:00 PM | Lunch |
2:00 - 2:45 PM | Keynote 6: Ruigang Yang, "3D Vision Research and Applications at Baidu" |
2:45 - 3:10 PM | Coffee Break |
3:10 - 3:50 PM | Oral Session 6 |
3:50 - 4:20 PM | Spotlight Session 5 |
4:20 - 5:20 PM | Poster session 3 |
5:20 - 6:20 PM | Awards, Closing Remarks and 3DV-18 |
Conference Program Details
Oral Session 1
Session Chair: Ping Tan
-
DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition
-
Sparsity Invariant CNNs
Spotlight Session 1
Session Chair: Ping Tan
-
A Novel Self-Calibration Method for a Stereo-ToF System Using a Kinect V2 and Two 4K GoPro Cameras
-
4D Temporally Coherent Dynamic Light-field Video
-
NERF: Dynamic High Resolution Deformable Articulated Tracking
-
High Dynamic Range SLAM with Map-Aware Exposure Time Control
Oral Session 2
Session Chair: Gabriel Taubin
-
OctNetFusion: Learning Depth Fusion from Data
-
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
Poster Session 1
-
Scalable Dense Monocular Surface Reconstruction
-
Compact Model Representation for 3D Reconstruction
-
Tracking Radioactive Sources through Sensor Fusion of Omnidirectional LIDAR and Isotropic Rad-detectors
-
Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles
-
Continuous Signed Distance Functions for 3D Vision
-
Interactive 3D Modeling with a Generative Adversarial Network
-
How to Refine 3D Hand Pose Estimation from Unlabelled Depth Data ?
-
Adversarially Parameterized Optimization for 3D Human Pose Estimation
-
GlobalSLAM: Initialization-robust Monocular Visual SLAM
Oral Session 3
Session Chair: Jan Michael Frahm
-
GraphMatch: Efficient Large-Scale Graph Construction for Structure from Motion
-
Fast Incremental Bundle Adjustment with Covariance Recovery
Spotlight Session 2
Session Chair: Jan Michael Frahm
-
Relative Camera Refinement for Accurate Dense Reconstruction
-
Line-based Robust SfM with Little Image Overlap
-
Batched Incremental Structure-from-Motion
-
Semi-Global Stereo Matching with Surface Orientation Prior
Oral Session 4
Session Chair: Adrian Hilton
-
Cascaded Scene Flow Prediction using Semantic Segmentation
-
Static and Dynamic Objects Analysis as a 3D Vector Field
Spotlight Session 3
Session Chair: Adrian Hilton
-
Generalized Pose Estimation from Line Correspondences with Known Vertical Direction
-
The Two Lines Light Source (TLLS)
-
Weakly Supervised 3D Reconstruction with Manifold Constraint
-
Multiframe Scene Flow with Piecewise Rigid Motion
-
Camera Uncertainty Computation in Large 3D Reconstruction
-
Probabilistic Object Reconstruction with Online Loop Closure
-
Multi-Label Point Cloud Annotation by Selection of Sparse Control Points
Poster Session 2
-
Controllable Variation Synthesis for Surface Motion Capture
-
Variational Building Modeling from Urban MVS Meshes
-
High Dimensional Space Model for Dense Monocular Surface Recovery
-
Fast and Efficient Depth Map Estimation from Light Fields
-
Direct Multichannel Tracking
-
Loop-Closure Detection in Urban Scenes for Autonomous Robot Navigation
-
Fast and Accurate Satellite Multi-view Stereo using Edge-Aware Interpolation
-
Registration of 3D Point Clouds using Mean Shift Clustering on Rotations and Translations
-
Learning quadrangulated patches for 3D shape parameterization and completion
-
Symmetry-aware Facade Parsing with Occlusions
-
Unsupervised 3D Shape Induction from 2D Views of Multiple Objects
-
Hierarchical Surface Prediction for 3D Object Reconstruction
-
Towards Accurate Markerless Human Shape and Pose Estimation over Time
-
3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances
-
Reconstructing 3D Human Poses from Keyword Based Image Database Query
Oral Session 5
Session Chair: Guy Godin
-
Learning Human Motion Models for Long-term Predictions
-
Real-time Full-Body Motion Capture from Video and IMUs
Spotlight Session 4
Session Chair: Guy Godin
-
Performance Evaluation of 3D Correspondence Grouping Algorithms
-
Spatial maps: from low rank spectral to sparse spatial functional representations
-
Efficient Model-free Anthropometry from Depth Data
-
Robust 3D Human Motion Reconstruction Via Dynamic Template Construction
Oral Session 6
Session Chair: Dani Lischinski
-
Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
-
Efficient Deformable Shape Correspondence via Kernel Matching
Spotlight Session 5
Session Chair: Dani Lischinski
-
Using learning of speed to stabilize scale in monocular localization and mapping
-
SEGCloud: 3D Semantic Segmentation on Point Cloud
-
Fast Multiview 3D Scan Registration using Planar Structures
-
Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
-
3D Object Classification via Spherical Projections
-
Metric Monocular Depth from Small Motion Accelerated
Poster Session 3
-
Line Association and Vanishing Point Estimation with Binary Quadratic Programming
-
Scene Semantic Reconstruction from Egocentric RGB-D-Thermal Videos
-
Single View Parametric Building Reconstruction from Satellite Imagery
-
Accurate Calibration of Multiple Pan-Tilt Cameras for Live Broadcasts
-
Complete 3D Room Geometry Reconstruction Using Audio-Visual Sensors
-
Barcode: Global Binary Patterns for Fast Visual Inference
-
Cross-modal Attribute Transfer for Rescaling 3D Models
-
Point Cloud Registration With Virtual Interest Points from Implicit Quadric Surface Intersections
-
Motion Compensation for Phase-Shift Structured-Light Systems Based On a Total-Variation Framework
-
Matterport3D: Learning from RGB-D Data in Indoor Environments
-
Joint 3D Reconstruction of a Static Scene and Moving Objects
-
Fuzzy Correspondences For Robust Shape Registration