Scene Essence
Jiayan Qiu, Yiding Yang, Xinchao Wang, Dacheng Tao
2021Year
4Top-tier citations
Abstract
Figure 1 : Given an input image of a hotel room (a), we detect its scene objects in (b) and learn to identify the Scene Essence that comprises a collection of essential elements for recognizing the scene, as labeled by the yellow bounding boxes. The image with essential elements preserved but minor ones inpainted are shown in (c), which, still, would be visually recognized as a hotel room. Should we further wipe off elements from the Scene Essence, in this case the bed, the scene will be interpreted as a living room.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers4
- Dynamic Shadow Unveils Invisible Semantics for Video OutpaintingRuilin Li, Hang Yu, Jiayan QiuNeurIPS 2025 · 2 citations
- Shadow-Enlightened Image OutpaintingHang Yu, Ruilin Li, Shaorong Xie, Jiayan QiuCVPR 2024
- Understanding Interaction as You Need: Intention-Driven Pedestrian Behavior PredictionHang Yu, Yansen Yu, Jiayan QiuAAAI 2026
- Controllable Data Generation with Hierarchical Neural RepresentationsSheyang Tang, Xiaoyu Xu, Jiayan Qiu, Zhou WangICML 2025
Builds on4
- Free-Form Image Inpainting With Gated ConvolutionJiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen et al.ICCV 2019 · 1,990 citations
- Factorizable Graph Convolutional NetworksYiding Yang, Zunlei Feng, Mingli Song, Xinchao WangNeurIPS 2020 · 175 citations
- Learning Physical Graph Representations from Visual ScenesDaniel Bear, Chaofei Fan, Damian Mrowca, Yunzhu Li et al.NeurIPS 2020 · 88 citations
- Distilling Knowledge From Graph Convolutional NetworksYiding Yang, Jiayan Qiu, Mingli Song, Dacheng Tao et al.CVPR 2020
Related papers
- Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric LearningCan Küçüksözen, Yücel YemezCVPR 2025
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and MappingJustin Lazarow, Kai Kang, Afshin DehghanNeurIPS 2025 · 2 citations
- SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual GroundingRong Li, Shijie Li, Lingdong Kong, Xulei Yang et al.CVPR 2025
- 3D Spatial Recognition Without Spatially Labeled 3DZhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit GirdharCVPR 2021
- Bundle Pooling for Polygonal Architecture Segmentation ProblemHuayi Zeng, Kevin Joseph, Adam Vest, Yasutaka FurukawaCVPR 2020
