From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models
This addresses a bottleneck in scene graph generation for computer vision applications, though it appears incremental as it builds on existing vision-language models.
The paper tackles the problem of generating scene graphs with novel visual relation concepts by introducing an open-vocabulary framework based on sequence generation using vision-language models, achieving superior performance and enhancing downstream vision-language tasks.
Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks. Despite recent advancements, existing methods struggle to generate scene graphs with novel visual relation concepts. To address this challenge, we introduce a new open-vocabulary SGG framework based on sequence generation. Our framework leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm. Specifically, we generate scene graph sequences via image-to-text generation with VLM and then construct scene graphs from these sequences. By doing so, we harness the strong capabilities of VLM for open-vocabulary SGG and seamlessly integrate explicit relational modeling for enhancing the VL tasks. Experimental results demonstrate that our design not only achieves superior performance with an open vocabulary but also enhances downstream vision-language task performance through explicit relation modeling knowledge.