How we animated light and motion for 3D interior visualisation

In our interactive feature on small spaces, we showcased storage tips and lighting strategies through immersive 3D animations ...
IEEE

DTNLS: 3D Point Cloud Segmentation Based on 2D Image and 3D Point Cloud Double Texture Feature

Abstract: Panoramic segmentation of 3D point clouds is an essential and challenging technology for robots with 3D detection and measurement capabilities. In order to fuse the color information of 2D ...
IEEE

Spatial Coordinate Transformation for 3D Neural Implicit Mapping

Abstract: Implicit Neural Representation (INR)-based SLAM has a critical issue where all keyframes must be stored in memory for post-training whenever a remapping is needed due to the neural network's ...
GitHub

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

Generalizable active mapping in complex unknown environments remains a critical challenge for mobile robots. Existing methods, constrained by insufficient training data and conservative exploration ...
GitHub

Personal Implementation of the paper: Nuvo: Neural UV Mapping for Unruly 3D Representations

conda create -n nuvo python=3.9 conda activate nuvo pip install -r requirements.txt I used Pytorch 2.3.0 with CUDA 11.8. Other versions may work, but are not tested ...