Graph R-CNN for Scene Graph Generation
We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images. Our model contains a Relation Proposal Network (RePN) that efficiently deals with the quadratic number of potential relations between objects in an image. We also propose an attentional Graph Convolutional Network (aGCN) that effectively captures contextual information between objects and relations. Finally, we introduce a new evaluation metric that is more holistic and realistic than existing metrics. We report state-of-the-art performance on scene graph generation as evaluated using both existing and our proposed metrics.
Code (3)
Tasks
Graph GenerationScene Graph GenerationSimilar Papers 제목 키워드 기반
MIGS: Meta Image Generation from Scene Graphs
Generation of images from scene graphs is a promising direction towards explicit scene generation and manipulation. However, the images generated from the scene graphs lack quality, which in part comes due to high diffic…
DiversityImage GenerationImage Generation from Scene GraphsMeta-Learning+1Learning Visual Commonsense for Robust Scene Graph Generation
Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild. Perception errors often lead to nonsensical composit…
Graph GenerationScene Graph GenerationScene UnderstandingImage Scene Graph Generation (SGG) Benchmark
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection. Due to the …
AttributeGraph GenerationObjectobject-detection+4Unconditional Scene Graph Generation
Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of no…
Anomaly DetectionGraph GenerationImage GenerationObject+1Graph Canvas for Controllable 3D Scene Generation
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on…
In-Context LearningScene Generation