ICCV 2017 accepted papers on 3D vision
130 of the 621 papers accepted at ICCV 2017 (20.9%) are on 3D vision. They fall into 6 topics.
See ICCV 2017 in the interactive map
Submitting to ICCV? Checklist →
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 · 54 papers
- End-To-End Learning of Geometry and Context for Deep Stereo Regression (1,573 citations)
- Image-Based Localization Using LSTMs for Structured Feature Correlation (525 citations)
- Stereo DSO: Large-Scale Direct Sparse Visual Odometry With Stereo Cameras (420 citations)
- A Two-Streamed Network for Estimating Fine-Scaled Depth Maps From Single RGB Images (259 citations)
- Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map (177 citations)
- Unsupervised Learning of Stereo Matching (167 citations)
- Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios? (146 citations)
- From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping (125 citations)
- Learned Multi-Patch Similarity (119 citations)
- Learning High Dynamic Range From Outdoor Panoramas (114 citations)
- Unsupervised Adaptation for Deep Stereo (108 citations)
- Neural EPI-Volume Networks for Shape From Light Field (106 citations)
and 42 more in the interactive map.
Human pose estimation · 35 papers
- RMPE: Regional Multi-Person Pose Estimation (2,025 citations)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (1,519 citations)
- SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again (1,069 citations)
- BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects Without Using Depth (857 citations)
- Learning to Estimate 3D Hand Pose From Single RGB Images (806 citations)
- Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach (630 citations)
- Compositional Human Pose Regression (586 citations)
- Learning Feature Pyramids for Human Pose Estimation (559 citations)
- Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation (376 citations)
- Real-Time Hand Tracking Under Occlusion From an Egocentric RGB-D Sensor (280 citations)
- Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (247 citations)
- Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources (218 citations)
and 23 more in the interactive map.
Face and shape · 31 papers
- Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs (761 citations)
- Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression (467 citations)
- MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (400 citations)
- Towards Large-Pose Face Frontalization in the Wild (358 citations)
- High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference (333 citations)
- A Joint Intrinsic-Extrinsic Prior Model for Retinex (316 citations)
- Deep Functional Maps: Structured Prediction for Dense Shape Correspondence (306 citations)
- Unrestricted Facial Geometry Reconstruction Using Image-To-Image Translation (283 citations)
- Raster-To-Vector: Revisiting Floorplan Transformation (270 citations)
- A Generative Model of People in Clothing (240 citations)
- 3D-PRNN: Generating Shape Primitives With Recurrent Neural Networks (202 citations)
- Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks (180 citations)
and 19 more in the interactive map.
3D generation · 7 papers
- DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding (69 citations)
- Monocular Dense 3D Reconstruction of a Complex Dynamic Scene From Two Perspective Frames (68 citations)
- FoveaNet: Perspective-Aware Urban Scene Parsing (57 citations)
- Probabilistic Structure From Motion With Objects (PSfMO) (40 citations)
- Semantically Informed Multiview Surface Refinement (36 citations)
- Embedding 3D Geometric Features for Rigid Object Part Segmentation (25 citations)
- Automatic Content-Aware Projection for 360deg Videos
Gaussian splatting · 2 papers
- Submodular Trajectory Optimization for Aerial 3D Scanning (160 citations)
- Space-Time Localization and Mapping (3 citations)
NeRF and radiance fields · 1 paper
- Learning to Synthesize a 4D RGBD Light Field From a Single Image (243 citations)
