learning-topology-synthetic-data
simplerecon
Our great sponsors
| learning-topology-synthetic-data | simplerecon | |
|---|---|---|
| 5 | 4 | |
| 37 | 1,205 | |
| - | 1.7% | |
| 4.3 | 3.3 | |
| 9 months ago | 11 months ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
learning-topology-synthetic-data
-
Want to use synthetic data, but don't want to deal with domain gap?
For those interested, here are our source code with pretrained mdoels (it is light-weight so it runs on your local machine!) and arxiv version of our paper.
paper: https://arxiv.org/pdf/2106.02994.pdf
Here are some of the reconstructions produced by our method:
https://github.com/alexklwong/learning-topology-synthetic-da...
https://github.com/alexklwong/learning-topology-synthetic-da...
-
[N][R] Want to leverage synthetic data for 3d reconstruction, but don't want to deal with the photometric domain gap? (ICRA 2021 talk)
Code for https://arxiv.org/abs/2106.02994 found: https://github.com/alexklwong/learning-topology-synthetic-data
simplerecon
-
Real time 3D reconstruction with SimpleRecon
An app would soon be there I think for iPad as well. Right now they have made the code public here: https://github.com/nianticlabs/simplerecon
-
SimpleRecon: A Computer Vision Framework that Produces 3D Reconstructions Without the Use of 3D Convolutions
Continue reading | Check out the paper and github link
- SIMPLERECON — 3D Reconstruction without 3D Convolutions — 73ms per frame !
What are some alternatives?
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
dream-creator - Quickly and easily create / train a custom DeepDream model
bpycv - Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
IGEV - [CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo
student-teacher-anomaly-detection - Student–Teacher Anomaly Detection with Discriminative Latent Embeddings
calibrated-backprojection-network - PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)
DECA - DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
Monocular-Depth-Estimation-Toolbox - Monocular Depth Estimation Toolbox based on MMSegmentation.
unsupervised-depth-completion-visual-inertial-odometry - Tensorflow and PyTorch implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
FusionConverter - Design files for the open-hardware NeoGeo MVS to AES converter
Make-It-3D - [ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior