analiza aiqbench
T-FunS3D introduces a task-driven hierarchical approach to 3D functionality segmentation that balances granularity, accuracy, and efficiency for robotic applications. By leveraging a vision-language model to query an open-vocabulary scene graph, the method achieves state-of-the-art performance on the SceneFun3D dataset while significantly reducing runtime and memory consumption compared to exhaustive scene-wide segmentation. This work advances actionable perception in robotics by addressing the resource-intensive nature of current part segmentation techniques.
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation
arXiv:2606.05975v1 Announce Type: cross Abstract: Open-vocabulary 3D functionality segmentation enables robots to localize functional object components in 3D scenes. It is a challenging task that requires spatial understanding and task interpretation. Current open-vocabulary 3D segmentation methods primarily focus on object-level recognition, while scene-wide part segmentation methods attempt to segment the entire scene exhaustively, making them highly resource-intensive and time consuming. Balancing segmentation performance in terms of granularity, accuracy, and speed remains a challenge. As one step towards alleviating this, we introduce T-FunS3D, a task-driven hierarchical open-vocabulary 3D functionality segmentation method that provides actionable perception for robotic applications. Our method takes as input the 3D point cloud and posed RGB-D images of an indoor scene. We construct an open-vocabulary scene graph by extracting instances and their visual embeddings in the environment. Given a task description, T-FunS3D identifies the most relevant instances in the scene graph and locates their functional components leveraging a vision-language model. Experiments on the SceneFun3D dataset demonstrate that T-FunS3D is comparable to state-of-the-art in open-vocabulary 3D functionality segmentation, while achieving faster runtime and reduced memory usage.
Abstract:Open-vocabulary 3D functionality segmentation enables robots to localize functional object components in 3D scenes. It is a challenging task that requires spatial understanding and task interpretation. Current open-vocabulary 3D segmentation methods primarily focus on object-level recognition, while scene-wide part segmentation methods attempt to segment the entire scene exhaustively, making them highly resource-intensive and time consuming. Balancing segmentation performance in terms of granularity, accuracy, and speed remains a challenge. As one step towards alleviating this, we introduce T-FunS3D, a task-driven hierarchical open-vocabulary 3D functionality segmentation method that provides actionable perception for robotic applications. Our method takes as input the 3D point cloud and posed RGB-D images of an indoor scene. We construct an open-vocabulary scene graph by extracting instances and their visual embeddings in the environment. Given a task description, T-FunS3D identifies the most relevant instances in the scene graph and locates their functional components leveraging a vision-language model. Experiments on the SceneFun3D dataset demonstrate that T-FunS3D is comparable to state-of-the-art in open-vocabulary 3D functionality segmentation, while achieving faster runtime and reduced memory usage.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2606.05975 [cs.CV]
(or arXiv:2606.05975v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.05975 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 272 cuvinte
Subiecte conexe
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
arXiv · 7 aug. 2026
Modernizing and scaling support operations with generative AI on AWS
AWS · 2 sept. 2026
GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision
arXiv · 15 oct. 2026
Salesforce after Dreamforce: How the CRM giant can grow beyond its own interface
SiliconANGLE · 19 sept. 2026