deep-video-mvs
ACMMP
deep-video-mvs | ACMMP | |
---|---|---|
1 | 1 | |
205 | 163 | |
- | - | |
0.0 | 0.0 | |
almost 3 years ago | 7 months ago | |
Python | C++ | |
MIT License | 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.
deep-video-mvs
-
helpful pointers to state-of-the-art material for depth estimation from multi-view videos captured from cameras with arbitrary poses.
If deep learning is an option, then you might want to check out http://zak.murez.com/atlas/, https://zju3dv.github.io/neuralrecon/, https://github.com/ardaduz/deep-video-mvs and the references therein. These methods can be better than classical ones, especially if overfitted on a specific type of scene.
ACMMP
-
helpful pointers to state-of-the-art material for depth estimation from multi-view videos captured from cameras with arbitrary poses.
That said, for classical 3D reconstruction from images, COLMAP is by far the best method in terms of usability - performances tradeoff. You can get something a bit better (such as https://github.com/GhiXu/ACMMP), but it is not very user-friendly.
What are some alternatives?
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
BundleFusion - [Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration
nerf-pytorch - A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
OpenMVG (open Multiple View Geometry) - open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
SGDepth - [ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
STEPS - This is the official repository for ICRA-2023 paper "STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation"
simplerecon - [ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
SiftGPU