3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, which is essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely ...
A Russian-linked campaign delivers the StealC V2 information stealer malware through malicious Blender files uploaded to 3D ...
We present Open3D-VQA, a novel benchmark for evaluating MLLMs' ability to reason about complex spatial relationships from an aerial perspective.The QAs are automatically generated from spatial ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback