Abstract: We present a novel framework for non-prehensile shape manipulation of deformable objects using Deep Reinforcement Learning. Unlike previous approaches that rely on grasping, our method ...

This is the official code for the ECCV 2024 paper "Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models". The format of the dataset is as ...

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 ...

As 2025 came to an end, scientists, governments and ordinary people across the world are still trying to understand some of the most unusual events of the past year. These events were widely reported, ...

Abstract: The detection of dynamic feature points presents a substantial challenge to dynamic scene analysis for simultaneous localization and mapping (SLAM). Conventional methods based on semantic ...

2025 brought us political, cultural and economic chaos, but it also gave us plenty of tangible objects to obsess over, buy and meme. There were the silly, monster-like dolls that sparked a craze among ...