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 ...
IEEE

Visual Boundary-Guided Pseudo-Labeling for Weakly Supervised 3D Point Cloud Segmentation in Indoor Environments

Abstract: Accurate segmentation of 3D point clouds in indoor scenes remains a challenging task, often hindered by the labor-intensive nature of data annotation. While weakly supervised learning ...
Los Angeles Times

L.A. defies the skeptics for a World Cup marked by unity, mutual respect, fearlessness

This is read by an automated voice. Please report any issues or inconsistencies here. But on the streets of L.A. over the last week, something very different has happened. Fans from a kaleidoscope of ...
IEEE

MSALNet: Capturing Contextual Relationships for Monocular 3D Visual Grounding

Abstract: Monocular 3D Visual Grounding (Mono3DVG) aims to predict the 3D localization of objects in monocular RGB images based on natural language descriptions. This task has broad applications in ...