stereo-image-generation
calibrated-backprojection-network
stereo-image-generation | calibrated-backprojection-network | |
---|---|---|
2 | 3 | |
33 | 112 | |
- | - | |
10.0 | 0.0 | |
over 1 year ago | 10 months ago | |
Python | Python | |
- | 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.
stereo-image-generation
-
I have a Rokid Air and am looking for suggestions as to how to include it in a HS classroom.
In context computer science class, for example, you may consider familiarizing students with generating stereo SBS image based on images of their choosing, perhaps using stable-diffusion-webui-depthmap-script (works in A1111 UI), or to keep things more focused https://github.com/m5823779/stereo-image-generation (no UI, but very simple to use in command-line).
-
3D side by side images (cross your eyes slowly until the images superimpose and you will see in 3D)
I started from that repository but it didn't work and had to rework a lot of what was there to make it better and more optimized. I can't share my code ATM because it's in draft-state (meaning : horrible mess) and I'm still working a lot on it but I couldn't resist to share a few of my results!
calibrated-backprojection-network
-
ICCV2021 oral paper improves generalization across sensor platforms
Our work "Unsupervised Depth Completion with Calibrated Backprojection Layers" has been accepted as an oral paper at ICCV 2021! We will be giving our talk during Session 10 (10/13 2-3 pm PST / 5-6 pm EST and 10/15 7-8 am PST / 10-11 am EST, https://www.eventscribe.net/2021/ICCV/fsPopup.asp?efp=WlJFS0tHTEMxNTgzMA%20&PosterID=428697%20&rnd=0.4100732&mode=posterinfo). This is joint work with Stefano Soatto at the UCLA Vision Lab.
In a nutshell: we propose a method for point cloud densification (from camera, IMU, range sensor) that can generalize well across different sensor platforms. The figure in this link illustrates our improvement over existing works: https://github.com/alexklwong/calibrated-backprojection-network/blob/master/figures/overview_teaser.gif
The slightly longer version: previous methods, when trained on one sensor platform, have problem generalizing to different ones when deployed to the wild. This is because they are overfitted to the sensors used to collect the training set. Our method takes image, sparse point cloud and camera calibration as input, which allows us to use a different calibration at test time. This significantly improves generalization to novel scenes captured by sensors different than those used during training. Amongst our innovations is a "calibrated backprojection layer" that imposes strong inductive bias on the network (as opposed trying to learn everything from the data). This design allows our method to achieve the state of the art on both indoor and outdoor scenarios while using a smaller model size and boasting a faster inference time.
For those interested, here are the links to
paper: https://arxiv.org/pdf/2108.10531.pdf
code (pytorch): https://github.com/alexklwong/calibrated-backprojection-network
-
[R] ICCV2021 oral paper -- Unsupervised Depth Completion with Calibrated Backprojection Layers improves generalization across sensor platforms
Code for https://arxiv.org/abs/2108.10531 found: https://github.com/alexklwong/calibrated-backprojection-network
What are some alternatives?
SincNet - SincNet is a neural architecture for efficiently processing raw audio samples.
EasyCV - An all-in-one toolkit for computer vision
cnnimageretrieval-pytorch - CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch
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)
edge-connect - EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
manydepth - [CVPR 2021] Self-supervised depth estimation from short sequences
merged_depth - Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
NeuralRecon - Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
simplerecon - [ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
3d-transforms - 3D Transforms is a library to easily work with 3D data and make 3D transformations. This library originally started as a few functions here and there for my own work which I then turned into a library.