Scene Understanding

On Equivariant and Invariant Learning of Object Landmark Representations ICCV 2021 OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets CVPR 2021 OSCAR-Net: Object-Centric Scene Graph Attention for Image Attribution ICCV 2021 Panoptic 3D Scene Reconstruction From a Single RGB Image NeurIPS 2021 Part-Aware Panoptic Segmentation CVPR 2021 Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition CVPR 2021 PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception AAAI 2021 Photon-Starved Scene Inference Using Single Photon Cameras ICCV 2021 Plan2Scene: Converting Floorplans to 3D Scenes CVPR 2021 Populating 3D Scenes by Learning Human-Scene Interaction CVPR 2021 PQA: Perceptual Question Answering CVPR 2021 Primitive Representation Learning for Scene Text Recognition CVPR 2021 Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation CVPR 2021 Progressive Correspondence Pruning by Consensus Learning ICCV 2021 Progressive Semantic Segmentation CVPR 2021 Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation CVPR 2021 PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning NeurIPS 2021 Pushing It Out of the Way: Interactive Visual Navigation CVPR 2021 Pyramid Point Cloud Transformer for Large-Scale Place Recognition ICCV 2021 QPIC: Query-Based Pairwise Human-Object Interaction Detection With Image-Wide Contextual Information CVPR 2021 Quantum Permutation Synchronization CVPR 2021 RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (Extended Abstract) IJCAI 2021 Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition CVPR 2021 Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform ICCV 2021 Refer-It-in-RGBD: A Bottom-Up Approach for 3D Visual Grounding in RGBD Images CVPR 2021