francisengelmann

PyViz3D

PyViz3D is a web-based visualizer for 3D objects and point clouds.

fast_voxel_traversal

Fast and simple voxel traversal algorithm through a 3D space partition.

FabScan100

FabScan1.5

FabScan

Affordable 3D Laser Scanning of Physical Objects

3D-MPA

[CVPR 2020] Multi Proposal Aggregation for 3D Semantic Instance Segmentation

points2objects

DPC

[ICRA 2020] Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

mcmc

Simple and basic implementation of MCMC-MH and sudoku solver using mcmc.

sound

Some tools to visualize audio input using OpenAL and FFTW

VisiCutHomography

Accurate live positioning for your lasercutter using VisiCut.

viz

Converter

Converter converts different file formats into other file formats.

GraphConvNets

visual_odometry

ARKitScenes

diffusion_models

francisengelmann.github.io

Human3D

We propose the first multi-human body-part segmentation model, called Human3D 🧑‍🤝‍🧑, that directly operates on 3D scenes. In an extensive analysis, we validate the benefits of training on synthetic data on multiple baselines and tasks.

Mask3D

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

nerfstudio

A collaboration friendly studio for NeRFs

replica_tools

road_plane

Compute road plane from stereo images using neural net.

ScanNet

vim

WACV-2023-Author-Kit