ECCV 2018 accepted papers on 3D vision
170 of the 776 papers accepted at ECCV 2018 (21.9%) are on 3D vision, compared with 25.8% at ECCV 2016. They fall into 6 topics.
See ECCV 2018 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 · 67 papers
- MVSNet: Depth Inference for Unstructured Multi-view Stereo (1,634 citations)
- DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency (494 citations)
- StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (427 citations)
- Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network (372 citations)
- Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry (356 citations)
- OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas (244 citations)
- Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow (232 citations)
- DeepTAM: Deep Tracking and Mapping (226 citations)
- Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss (216 citations)
- Learning Monocular Depth by Distilling Cross-domain Stereo Networks (210 citations)
- Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images (203 citations)
- Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation (194 citations)
and 55 more in the interactive map.
Human pose estimation · 53 papers
- Simple Baselines for Human Pose Estimation and Tracking (2,290 citations)
- Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera (1,113 citations)
- Integral Human Pose Regression (955 citations)
- PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model (660 citations)
- DeepIM: Deep Iterative Matching for 6D Pose Estimation (586 citations)
- Implicit 3D Orientation Learning for 6D Object Detection from RGB Images (575 citations)
- BOP: Benchmark for 6D Object Pose Estimation (491 citations)
- Exploiting temporal information for 3D human pose estimation (439 citations)
- BodyNet: Volumetric Inference of 3D Human Body Shapes (433 citations)
- RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (420 citations)
- MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (322 citations)
- Hand Pose Estimation via Latent 2.5D Heatmap Regression (320 citations)
and 41 more in the interactive map.
Face and shape · 30 papers
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (1,416 citations)
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (774 citations)
- Generating 3D Faces using Convolutional Mesh Autoencoders (598 citations)
- Learning Category-Specific Mesh Reconstruction from Image Collections (558 citations)
- 3D-CODED: 3D Correspondences by Deep Deformation (314 citations)
- DeepWrinkles: Accurate and Realistic Clothing Modeling (230 citations)
- GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints (195 citations)
- Learning Shape Priors for Single-View 3D Completion and Reconstruction (187 citations)
- Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance (183 citations)
- FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans (145 citations)
- A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment (104 citations)
- Recovering 3D Planes from a Single Image via Convolutional Neural Networks (101 citations)
and 18 more in the interactive map.
3D generation · 14 papers
- 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation (354 citations)
- Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image (143 citations)
- Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence (130 citations)
- Efficient Semantic Scene Completion Network with Spatial Group Convolution (118 citations)
- Learning to Look around Objects for Top-View Representations of Outdoor Scenes (72 citations)
- Volumetric performance capture from minimal camera viewpoints (52 citations)
- Joint 3D tracking of a deformable object in interaction with a hand (49 citations)
- Large Scale Urban Scene Modeling from MVS Meshes (40 citations)
- Extending Layered Models to 3D Motion (30 citations)
- End-to-End Deep Structured Models for Drawing Crosswalks (25 citations)
- Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video (23 citations)
- Specular-to-Diffuse Translation for Multi-View Reconstruction (23 citations)
and 2 more in the interactive map.
Gaussian splatting · 3 papers
- Semi-Dense 3D Reconstruction with a Stereo Event Camera (172 citations)
- Layer-structured 3D Scene Inference via View Synthesis (156 citations)
- Super-Resolution and Sparse View CT Reconstruction (30 citations)
