6 papers
LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
Jiangyong Huang, Xiaojian Ma, Xiongkun Linghu +6
Developing vision-language models (VLMs) capable of understanding 3D scenes has been a longstanding research goal. Despite recent progress, 3D VLMs still struggle with spatial reas…
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
Ziyu Zhu, Xilin Wang, Yixuan Li +9
Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world.…
MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans
Huangyue Yu, Baoxiong Jia, Yixin Chen +9
Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality stan…
Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis
Jiangyong Huang, Baoxiong Jia, Yan Wang +5
Existing 3D vision-language (3D-VL) benchmarks fall short in evaluating 3D-VL models, creating a "mist" that obscures rigorous insights into model capabilities and 3D-VL tasks. Thi…
Task-oriented Sequential Grounding and Navigation in 3D Scenes
Zhuofan Zhang, Ziyu Zhu, Junhao Li +8
Grounding natural language in 3D environments is a critical step toward achieving robust 3D vision-language alignment. Current datasets and models for 3D visual grounding predomina…
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
Rujie Wu, Xiaojian Ma, Zhenliang Zhang +4
We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision. It originates from the classical Bongard Problems (BPs): Given two…