angeladai / Scancomplete
Licence: apache-2.0
[CVPR'18] ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
Stars: ✭ 213
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Scancomplete
Tf flame
Tensorflow framework for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 2D or 3D keypoints, and how to generate textured head meshes from Images.
Stars: ✭ 193 (-9.39%)
Mutual labels: computer-graphics, 3d-reconstruction
instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
Stars: ✭ 1,863 (+774.65%)
Mutual labels: computer-graphics, 3d-reconstruction
PointCloudRegistrationTool
Automatically registers (aligns) and visualizes point clouds, or processes a whole bunch at once
Stars: ✭ 82 (-61.5%)
Mutual labels: computer-graphics, 3d-reconstruction
Structured3d
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
Stars: ✭ 224 (+5.16%)
Mutual labels: computer-graphics, 3d-reconstruction
Pifu
This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
Stars: ✭ 1,021 (+379.34%)
Mutual labels: computer-graphics, 3d-reconstruction
platonicgan
Escaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]
Stars: ✭ 40 (-81.22%)
Mutual labels: computer-graphics, 3d-reconstruction
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+200.94%)
Mutual labels: computer-graphics, 3d-reconstruction
Flame Fitting
Example code for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 3D keypoints and 3D scans.
Stars: ✭ 269 (+26.29%)
Mutual labels: computer-graphics, 3d-reconstruction
Softras
Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"
Stars: ✭ 715 (+235.68%)
Mutual labels: computer-graphics, 3d-reconstruction
Cnncomplete
[CVPR'17] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis
Stars: ✭ 117 (-45.07%)
Mutual labels: computer-graphics, 3d-reconstruction
Sgnn
[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Stars: ✭ 112 (-47.42%)
Mutual labels: computer-graphics, 3d-reconstruction
Flame pytorch
This is a implementation of the 3D FLAME model in PyTorch
Stars: ✭ 153 (-28.17%)
Mutual labels: computer-graphics, 3d-reconstruction
Tinykaboom
A brief computer graphics / rendering course
Stars: ✭ 2,077 (+875.12%)
Mutual labels: computer-graphics
Light Field Video
Light field video applications (e.g. video refocusing, focus tracking, changing aperture and view)
Stars: ✭ 190 (-10.8%)
Mutual labels: computer-graphics
Factored3d
Code release for "Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene"
Stars: ✭ 170 (-20.19%)
Mutual labels: 3d-reconstruction
Gerbolyze
Render high-resolution bitmap images to PCB gerber files
Stars: ✭ 169 (-20.66%)
Mutual labels: computer-graphics
Pixel2meshplusplus
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.
Stars: ✭ 188 (-11.74%)
Mutual labels: 3d-reconstruction
Deodr
A differentiable 3D renderer with Pytorch, Tensorflow and Matlab interfaces
Stars: ✭ 167 (-21.6%)
Mutual labels: 3d-reconstruction
Oanet
Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"
Stars: ✭ 166 (-22.07%)
Mutual labels: 3d-reconstruction
ScanComplete
ScanComplete is a data-driven approach which takes an incomplete 3D scan of a scene as input and predicts a complete 3D model, along with per-voxel semantic labels. This work is based on our CVPR'18 paper, ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans.
Code
Installation:
Training is implemented with TensorFlow. This code is tested under TF1.3 and Python 2.7 on Ubuntu 16.04.
Training:
- See
run_train.shfor calling the training (will need to provide a path to the train data). - Trained models: models.zip
Testing:
- See
run_complete_scans_hierarchical.shfor testing on partial scans (needs paths to test data and model).
Citation:
If you find our work useful in your research, please consider citing:
@inproceedings{dai2018scancomplete,
title={ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans},
author={Dai, Angela and Ritchie, Daniel and Bokeloh, Martin and Reed, Scott and Sturm, J{\"u}rgen and Nie{\ss}ner, Matthias},
booktitle = {Proc. Computer Vision and Pattern Recognition (CVPR), IEEE},
year = {2018}
}
Contact:
If you have any questions, please email Angela Dai at [email protected].
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].