Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: Understanding how natural language phrases correspond to specific regions in
images is a key challenge in multimodal semantic segmentation. Recent advances
in phrase grounding are largely limited to single-view images, neglecting the
rich geometric cues available in stereo vision. For this, we introduce
PhraseStereo, the first novel dataset that brings phrase-region segmentation to
stereo image pairs. PhraseStereo builds upon the PhraseCut dataset by
leveraging GenStereo to generate accurate right-view images from existing
single-view data, enabling the extension of phrase grounding into the stereo
domain. This new setting introduces unique challenges and opportunities for
multimodal learning, particularly in leveraging depth cues for more precise and
context-aware grounding. By providing stereo image pairs with aligned
segmentation masks and phrase annotations, PhraseStereo lays the foundation for
future research at the intersection of language, vision, and 3D perception,
encouraging the development of models that can reason jointly over semantics
and geometry. The PhraseStereo dataset will be released online upon acceptance
of this work.
Key Contributions
Introduces PhraseStereo, the first dataset for phrase-region segmentation in stereo image pairs, extending phrase grounding to leverage rich geometric cues from stereo vision. This dataset enables research into multimodal learning that utilizes depth information for more precise and context-aware grounding.
Business Value
Enables more sophisticated visual understanding systems for applications like autonomous driving, robotics, and augmented reality by allowing them to precisely identify objects and regions described by natural language in 3D environments.