Tech Xplore

Two-stage framework reconstructs sharp 4D scenes from blurry handheld videos

Neural Radiance Fields (NeRF) is a fascinating technique that creates three-dimensional (3D) representations of a scene from ...
GitHub

[ICLR 2025] Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for ...
GitHub

Any6D: Model-free 6D Pose Estimation of Novel Objects

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike ...
IEEE

MV-YOLO: An Efficient Small Object Detection Framework Based on Mamba

Abstract: Small-object detection in uncrewed aerial vehicle (UAV) and remote-sensing imagery remains challenging because targets occupy only a few pixels, features are sparse, objects are often ...
IEEE

An End-to-End Large Model Framework of Wearable Augmented Vision Device for the Visually Impaired

Abstract: Visual impairments significantly affect individuals’ ability to perform essential tasks such as communication, object search, and navigation. Traditional wearable augmented vision devices ...