Pix2Vox
unsupervised-depth-completion-visual-inertial-odometry
Pix2Vox | unsupervised-depth-completion-visual-inertial-odometry | |
---|---|---|
1 | 2 | |
439 | 185 | |
- | - | |
3.5 | 5.0 | |
3 months ago | 10 months ago | |
Python | Python | |
MIT License | 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.
Pix2Vox
-
[need help] I am trying to do 3d object reconstruction using rgbd images from kinnect device.
I am trying to achieve what this paper is doing https://github.com/hzxie/Pix2Vox but this paper is using only RGB images. I want to introduce depth in it as well. So for example, I will place a cup on table and get its different snapshots from different orientations using the Kinnect 2 device. These images will be passed through some pipeline of algorithms (can be ml or dl) to get Voxels (cup or object as a volume).
unsupervised-depth-completion-visual-inertial-odometry
-
Unsupervised Depth Completion from Visual Inertial Odometry
Hey there, interested in camera and range sensor fusion for point cloud (depth) completion?
Here is an extended version of our [talk](https://www.youtube.com/watch?v=oBCKO4TH5y0) at ICRA 2020 where we do a step by step walkthrough of our paper Unsupervised Depth Completion from Visual Inertial Odometry (joint work with Fei Xiaohan, Stephanie Tsuei, and Stefano Soatto).
In this talk, we present an unsupervised method (no need for human supervision/annotations) for learning to recover dense point clouds from images, captured by cameras, and sparse point clouds, produced by lidar or tracked by visual inertial odometry (VIO) systems. To illustrate what I mean, here is an [example](https://github.com/alexklwong/unsupervised-depth-completion-visual-inertial-odometry/blob/master/figures/void_teaser.gif?raw=true) of the point clouds produced by our method.
Our method is light-weight (so you can run it on your computer!) and is built on top of [XIVO] (https://github.com/ucla-vision/xivo) our VIO system.
For those interested here are links to the [paper](https://arxiv.org/pdf/1905.08616.pdf), [code](https://github.com/alexklwong/unsupervised-depth-completion-visual-inertial-odometry) and the [dataset](https://github.com/alexklwong/void-dataset) we collected.
-
[N][R] ICRA 2020 extended talk for Unsupervised Depth Completion from Visual Inertial Odometry
In this talk, we present an unsupervised method (no need for human supervision/annotations) for learning to recover dense point clouds from images, captured by cameras, and sparse point clouds, produced by lidar or tracked by visual inertial odometry (VIO) systems. To illustrate what I mean, you can visit our github page for examples (gifs) of point clouds produced by our method.
What are some alternatives?
DeblurGANv2 - [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
Pointnet_Pointnet2_pytorch - PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
dino - PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
IGR - Implicit Geometric Regularization for Learning Shapes
calibrated-backprojection-network - PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)
2dimageto3dmodel - We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.
xivo - X Inertial-aided Visual Odometry
PIFu - This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
simclr - SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
void-dataset - Visual Odometry with Inertial and Depth (VOID) dataset
bpycv - Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)