IEEE

Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-Labeling

Abstract: Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised ...
Wall Street Journal

Ukraine Depended on Western Weaponry. Now That Script Has Flipped.

MUNICH—When the full-scale Russian invasion began, Western defense manufacturers rushed their modern weaponry into Ukraine, helping Kyiv drive back a much more powerful foe. Four years on, the flow of ...
GitHub

Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding

Comparative overview of two 3DVG approaches. (a) Supervised 3DVG involves input from 3D scans combined with text queries, guided by object-text pair annotations, (b) Zero-shot 3DVG identifies the ...
IEEE

Manipulating the Bounding Box: Multimodal Controlled Backdoor Attacks on 3D Visual Grounding Models

Abstract: 3D visual grounding models, pivotal in interpreting and aligning objects within 3D spaces with textual descriptions, have become integral to the advancement of the multimedia community. As ...
GitHub

Z3D: Zero-Shot 3D Visual Grounding from Images

This repository contains an implementation of Z3D, a zero-shot method for 3d visual grounding introduced in our paper: You also need to run a vLLM server to host the ...