involution
manydepth
| involution | manydepth | |
|---|---|---|
| 6 | 2 | |
| 1,306 | 594 | |
| - | 0.7% | |
| 0.0 | 0.0 | |
| almost 3 years ago | 9 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.
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
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.
What are some alternatives?
efficientdet-pytorch - A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
VIBE - Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
mmdetection - OpenMMLab Detection Toolbox and Benchmark
calibrated-backprojection-network - PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)
Im2Vec - [CVPR 2021 Oral] Im2Vec Synthesizing Vector Graphics without Vector Supervision
STEPS - This is the official repository for ICRA-2023 paper "STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation"
yolact_edge - The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
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)
unilm - Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
second.pytorch - SECOND for KITTI/NuScenes object detection
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]