# On Support Relations and Semantic Scene Graphs

arXiv: https://arxiv.org/abs/1609.05834 · HTML: https://mlsanity.com/paper/1609.05834/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2016.

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [Spatial-Temporal Transformer for Dynamic Scene Graph Generation](https://mlsanity.com/paper/2107.12309/) (2021)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration](https://mlsanity.com/paper/2107.05080/) (2021)
- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [SPAN: Learning Similarity between Scene Graphs and Images with Transformers](https://mlsanity.com/paper/2304.00590/) (2023)
- [Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks](https://mlsanity.com/paper/2504.12817/) (2025)
- [On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments](https://mlsanity.com/paper/2404.13842/) (2024)
- [Generation of High-Level Concepts in 3D Scene Graphs via Autoregressive Diffusion](https://mlsanity.com/paper/2608.28733/) (2026)

## Abstract (arXiv)

Scene understanding is a popular and challenging topic in both computer vision and photogrammetry. Scene graph provides rich information for such scene understanding. This paper presents a novel approach to infer such relations and then to construct the scene graph. Support relations are estimated by considering important, previously ignored information: the physical stability and the prior support knowledge between object classes. In contrast to previous methods for extracting support relations, the proposed approach generates more accurate results, and does not require a pixel-wise semantic labeling of the scene. The semantic scene graph which describes all the contextual relations within the scene is constructed using this information. To evaluate the accuracy of these graphs, multiple different measures are formulated. The proposed algorithms are evaluated using the NYUv2 database. The results demonstrate that the inferred support relations are more precise than state-of-the-art. The scene graphs are compared against ground truth graphs.