SiftGPU
nerf-pytorch
| SiftGPU | nerf-pytorch | |
|---|---|---|
| 1 | 3 | |
| 365 | 5,052 | |
| - | - | |
| 10.0 | 0.0 | |
| almost 2 years ago | 4 months ago | |
| C++ | 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.
SiftGPU
-
helpful pointers to state-of-the-art material for depth estimation from multi-view videos captured from cameras with arbitrary poses.
Take a look at BundleFusion: Paper, Project Page, Source Code and SIFTGPU Source Code, used in BundleFusion source. It has a “server GPU” implementation
nerf-pytorch
-
[D] Something basic I don't understand about Nerfs
Found relevant code at https://github.com/yenchenlin/nerf-pytorch + all code implementations here
-
helpful pointers to state-of-the-art material for depth estimation from multi-view videos captured from cameras with arbitrary poses.
I have been curious about NeRF and have tried out the software. I really like the idea, but I have found generating the NeRF representation to be too slow and does not do seem to do too well if the number of cameras in the rig are a bit sparse. I have seen that there have been some evolution and variations of the NeRF concept and I am looking into some of them currently.
-
[P] Minimal PyTorch implementation of NeRF. Full model implementation and training code in 320 lines.
While there are other PyTorch implementations out there (e.g., this one and this one), I personally found them somewhat difficult to follow, so I decided to do a complete rewrite of NeRF myself. I tried to stay as close to the authors' text as possible, and I added comments in the code referring back to the relevant sections/equations in the paper. The final result is a tight 374 lines of heavily commented code (320 sloc—"source lines of code"—on GitHub) all contained in a single file. For comparison, this PyTorch implementation has approximately 970 sloc spread across several files, while this PyTorch implementation has approximately 905 sloc. A Colab notebook for the full model can be found here.
What are some alternatives?
OpenMVG (open Multiple View Geometry) - open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
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
pytorch-nerf - Minimal PyTorch implementations of NeRF and pixelNeRF.
ACMMP - Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (TPAMI 2022)
nerf-pytorch - A PyTorch re-implementation of Neural Radiance Fields
depthai - DepthAI Python API utilities, examples, and tutorials.
colmap - COLMAP - Structure-from-Motion and Multi-View Stereo
deep-video-mvs - Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)