Reproduce “OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Wenyuan Huang, Zhenyu Zhang, Zhao Wang, Zhou Wei, Ting Huang, Fang Zhao, Jian Yang

OpenGround addresses 3D visual grounding by planning a sequence of context-to-target subgoals and extending an object lookup table when the target is missing. It uses grounded context to guide views for segmentation and 3D object discovery. On OpenTarget with a Mask3D initial table, it achieves 34.2% [email protected], versus 8.6% for SeqVLM; this benchmark result is limited to designed part-level targets.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.