Compact Scene Graphs For Layout Composition And Patch Retrieval

Abstract

Structured representations such as scene graphs serve as an efficient and compact representation that can be used for downstream rendering or retrieval tasks. However, existing efforts to generate realistic images from scene graphs perform poorly on scene composition for cluttered or complex scenes. We propose two contributions to improve the scene composition. First, we enhance the scene graph representation with heuristic-based relations, which add minimal storage overhead. Second, we use extreme points representation to supervise the learning of the scene composition network. These methods achieve significantly higher performance over existing work (69.0% vs 51.2% in relation score metric). We additionally demonstrate how scene graphs can be used to retrieve pose-constrained image patches that are semantically similar to the source query. Improving structured scene graph representations for rendering or retrieval is an important step towards realistic image generation.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keytripathi2019compact

Related papers

• Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (2020)17.18
• Scene Graph Embeddings Using Relative Similarity Supervision (2021)7.50
• Image-to-image Retrieval By Learning Similarity Between Scene Graphs (2020)12.02
• Triplet-aware Scene Graph Embeddings (2019)7.81
• Scene Designer: A Unified Model For Scene Search And Synthesis From Sketch (2021)5.84
• SCENIR: Visual Semantic Clarity Through Unsupervised Scene Graph Retrieval (2025)0.00
• Scenarios: A New Representation For Complex Scene Understanding (2018)0.00
• Partially Does It: Towards Scene-level FG-SBIR With Partial Input (2022)10.97