manydepth
involution
manydepth | involution | |
---|---|---|
2 | 6 | |
596 | 1,306 | |
1.0% | - | |
0.0 | 0.0 | |
9 months ago | almost 3 years 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.
manydepth
-
How Many Sensors for Autonomous Driving?
Yup! This kind of reconstruction is known as multi-view reconstruction. Though the cameras don't need to have a movable mount, they're already on a car which moves! The car moves and gives them a new "perspective" at every frame. That's how some monocular systems already work. Here's an example of one such system: https://github.com/nianticlabs/manydepth
That said, I think what you're referring to is more extreme perspectives that shift in ways the car cannot drive and you are correct that this would aid in reconstruction. This is how NERF models do their 3D reconstruction (https://nerfies.github.io/).
-
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth – method outperforms all self-supervised methods on KITTI and Cityscapes
Looks like it's available now.
involution
-
[R] Involution: Inverting the Inherence of Convolution for Visual Recognition
PDF Link | Landing Page | Read as web page on arXiv Vanity
-
[P] PyTorch Involution layer wrapper
Have you benchmarked it against the official implementations? Would be interesting to see what the difference is versus their CUDA version.
-
[D] Paper Explained - Involution: Inverting the Inherence of Convolution for Visual Recognition (Full Video Analysis)
Code: https://github.com/d-li14/involution
What are some alternatives?
VIBE - Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
efficientdet-pytorch - A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
calibrated-backprojection-network - PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)
mmdetection - OpenMMLab Detection Toolbox and Benchmark
STEPS - This is the official repository for ICRA-2023 paper "STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation"
Im2Vec - [CVPR 2021 Oral] Im2Vec Synthesizing Vector Graphics without Vector Supervision
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)
yolact_edge - The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
second.pytorch - SECOND for KITTI/NuScenes object detection
unilm - Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
MPRNet - [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
MaskDINO - [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation" [Moved to: https://github.com/IDEA-Research/MaskDINO]