calibrated-backprojection-network
learning-topology-synthetic-data
calibrated-backprojection-network | learning-topology-synthetic-data | |
---|---|---|
3 | 5 | |
111 | 37 | |
- | - | |
0.0 | 4.3 | |
10 months ago | 10 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.
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
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
What are some alternatives?
EasyCV - An all-in-one toolkit for computer vision
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.
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)
bpycv - Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
manydepth - [CVPR 2021] Self-supervised depth estimation from short sequences
student-teacher-anomaly-detection - Student–Teacher Anomaly Detection with Discriminative Latent Embeddings
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark
DECA - DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
NeuralRecon - Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
simplerecon - [ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Make-It-3D - [ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior