IEEE

Enhanced Reward Function Design for Source Term Estimation Based on Deep Reinforcement Learning

Abstract: This study investigates the design of reward functions for deep reinforcement learning-based source term estimation (STE). Estimating the properties of unknown hazardous gas leakage using a ...
GitHub

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

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 ...
IEEE

Glissando-Net: Deep Single View Category Level Pose Estimation and 3D Reconstruction

Abstract: We present a deep learning model, dubbed Glissando-Net, to simultaneously estimate the pose and reconstruct the 3D shape of objects at the category level from a single RGB image. Previous ...
GitHub

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on ...