calibrated-backprojection-network
pytorch-metric-learning
calibrated-backprojection-network | pytorch-metric-learning | |
---|---|---|
3 | 3 | |
111 | 5,770 | |
- | - | |
0.0 | 7.9 | |
10 months ago | about 1 month ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
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.
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
pytorch-metric-learning
-
Similarity Learning lacks a framework. So we built one
Not a full featured framework, but pytorch-metric-learning has data loaders, lossess, etc. to facilitate similarity learning: https://github.com/KevinMusgrave/pytorch-metric-learning
Disclaimer: I've made some contributions to it.
-
[R][D] VAE Embedding Space - Can we force it to learn a metric?
You can use the triplet loss together with the Gaussian prior. It will be zero centered though and the clusters are not as separated when you use the triplet loss only.There are many alternative to the triplet loss, in case it needs to be a metric: https://github.com/KevinMusgrave/pytorch-metric-learning
-
[D] Similar Image Retrieval
This repo provides the tools and examples needed to build such a model: https://github.com/KevinMusgrave/pytorch-metric-learning
What are some alternatives?
EasyCV - An all-in-one toolkit for computer vision
dino - PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
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)
lightly - A python library for self-supervised learning on images.
manydepth - [CVPR 2021] Self-supervised depth estimation from short sequences
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark
byol-pytorch - Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
NeuralRecon - Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
autogluon - Fast and Accurate ML in 3 Lines of Code
simplerecon - [ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
simsiam-cifar10 - Code to train the SimSiam model on cifar10 using PyTorch