← Analysis
Computer Vision › Analysis ›

Scene Understanding

1887 directly classified papers

Papers per year

Papers

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation CVPR 2019
Using Unknown Occluders to Recover Hidden Scenes CVPR 2019
Deep Light-field-driven Saliency Detection from a Single View IJCAI 2019
HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation CVPR 2019
Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach IJCAI 2019
Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans ICCV 2019
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation CVPR 2019
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding CVPR 2019
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion CVPR 2019
Detect-To-Retrieve: Efficient Regional Aggregation for Image Search CVPR 2019
Knowledge-Embedded Routing Network for Scene Graph Generation CVPR 2019
SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations CVPR 2019
GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching CVPR 2019
CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions CVPR 2019
Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding CVPR 2019
Spatial-Aware Graph Relation Network for Large-Scale Object Detection CVPR 2019
Panoptic Segmentation CVPR 2019
All-Weather Deep Outdoor Lighting Estimation CVPR 2019
An End-To-End Network for Generating Social Relationship Graphs CVPR 2019
Graphical Contrastive Losses for Scene Graph Parsing CVPR 2019
Context-Aware Visual Compatibility Prediction CVPR 2019
Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting CVPR 2019
Consensus Maximization Tree Search Revisited ICCV 2019
SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition ICCV 2019
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints ICCV 2019