ECCV 2016 accepted papers on 3D vision
107 of the 415 papers accepted at ECCV 2016 (25.8%) are on 3D vision. They fall into 6 topics.
See ECCV 2016 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Depth and stereo · 37 papers
- Pixelwise View Selection for Unstructured Multi-View Stereo (2,478 citations)
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue (1,641 citations)
- Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera (445 citations)
- VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (311 citations)
- A Software Platform for Manipulating the Camera Imaging Pipeline (178 citations)
- Exploiting Semantic Information and Deep Matching for Optical Flow (109 citations)
- Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields (99 citations)
- Fast Guided Global Interpolation for Depth and Motion (98 citations)
- Shading-Aware Multi-view Stereo (93 citations)
- An Evaluation of Computational Imaging Techniques for Heterogeneous Inverse Scattering (91 citations)
- Linear Depth Estimation from an Uncalibrated, Monocular Polarisation Image (88 citations)
- All-Around Depth from Small Motion with a Spherical Panoramic Camera (83 citations)
and 25 more in the interactive map.
Human pose estimation · 33 papers
- Stacked Hourglass Networks for Human Pose Estimation (5,720 citations)
- Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (1,572 citations)
- DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model (1,217 citations)
- Human Pose Estimation via Convolutional Part Heatmap Regression (542 citations)
- Real-Time Joint Tracking of a Hand Manipulating an Object from RGB-D Input (252 citations)
- Chained Predictions Using Convolutional Neural Networks (195 citations)
- Fashion Landmark Detection in the Wild (177 citations)
- Deep Specialized Network for Illuminant Estimation (174 citations)
- Towards Viewpoint Invariant 3D Human Pose Estimation (171 citations)
- Human Pose Estimation Using Deep Consensus Voting (165 citations)
- Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation (162 citations)
- Deep Deformation Network for Object Landmark Localization (113 citations)
and 21 more in the interactive map.
Face and shape · 26 papers
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (1,765 citations)
- Learning a Predictable and Generative Vector Representation for Objects (682 citations)
- Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks (422 citations)
- Deep Learning 3D Shape Surfaces Using Geometry Images (307 citations)
- Single Image 3D Interpreter Network (252 citations)
- Deep Cascaded Bi-Network for Face Hallucination (251 citations)
- Counting in the Wild (248 citations)
- 3D Mask Face Anti-spoofing with Remote Photoplethysmography (194 citations)
- Joint Face Alignment and 3D Face Reconstruction (140 citations)
- Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure (132 citations)
- Towards Large-Scale City Reconstruction from Satellites (64 citations)
- A Symmetry Prior for Convex Variational 3D Reconstruction (58 citations)
and 14 more in the interactive map.
3D generation · 7 papers
- Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes (954 citations)
- View Synthesis by Appearance Flow (631 citations)
- “What Happens If...” Learning to Predict the Effect of Forces in Images (84 citations)
- Learning Semantic Deformation Flows with 3D Convolutional Networks (58 citations)
- SDF-2-SDF: Highly Accurate 3D Object Reconstruction (44 citations)
- Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding (9 citations)
- Semantic 3D Reconstruction of Heads (7 citations)
