Scene Understanding

PanelNet: Understanding 360 Indoor Environment via Panel Representation CVPR 2023 Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning CVPR 2023 Panoptic Video Scene Graph Generation CVPR 2023 PanoSwin: A Pano-Style Swin Transformer for Panorama Understanding CVPR 2023 PATS: Patch Area Transportation With Subdivision for Local Feature Matching CVPR 2023 Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties NeurIPS 2023 PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction ICCV 2023 Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding ICML 2023 Pixel-Wise Warping for Deep Image Stitching AAAI 2023 Placing Human Animations Into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes WACV 2023 Privacy Preserving Localization via Coordinate Permutations ICCV 2023 Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks CVPR 2023 Progressive Neighbor Consistency Mining for Correspondence Pruning CVPR 2023 Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes CVPR 2023 Puzzlefusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving NeurIPS 2023 PVO: Panoptic Visual Odometry CVPR 2023 Query-based Image Captioning from Multi-context 360cdegree Images EMNLP 2023 R2Former: Unified Retrieval and Reranking Transformer for Place Recognition CVPR 2023 RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation ICCV 2023 Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network EMNLP 2023 Referring to Screen Texts with Voice Assistants ACL 2023 Rethinking Optical Flow From Geometric Matching Consistent Perspective CVPR 2023 Reusable Slotwise Mechanisms NeurIPS 2023 Revisiting Self-Similarity: Structural Embedding for Image Retrieval CVPR 2023 RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments NeurIPS 2023