gnn-lspe
PET-NeuS
gnn-lspe | PET-NeuS | |
---|---|---|
3 | 1 | |
214 | 249 | |
- | - | |
0.0 | 5.5 | |
about 2 years ago | 11 months ago | |
Python | Python | |
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.
gnn-lspe
- [D] Machine Learning - WAYR (What Are You Reading) - Week 128
-
[R] Graph Neural Networks with Learnable Structural and Positional Representations
Code for https://arxiv.org/abs/2110.07875 found: https://github.com/vijaydwivedi75/gnn-lspe
PET-NeuS
-
PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces
A signed distance function (SDF) parametrized by an MLP is a common ingredient of neural surface reconstruction. We build on the successful recent method NeuS to extend it by three new components. The first component is to borrow the tri-plane representation from EG3D and represent signed distance fields as a mixture of tri-planes and MLPs instead of representing it with MLPs only. Using tri-planes leads to a more expressive data structure but will also introduce noise in the reconstructed surface. The second component is to use a new type of positional encoding with learnable weights to combat noise in the reconstruction process. We divide the features in the tri-plane into multiple frequency scales and modulate them with sin and cos functions of different frequencies. The third component is to use learnable convolution operations on the tri-plane features using self-attention convolution to produce features with different frequency bands. The experiments show that PET-NeuS achieves high-fidelity surface reconstruction on standard datasets. Following previous work and using the Chamfer metric as the most important way to measure surface reconstruction quality, we are able to improve upon the NeuS baseline by 57% on Nerf-synthetic (0.84 compared to 1.97) and by 15.5% on DTU (0.71 compared to 0.84). The qualitative evaluation reveals how our method can better control the interference of high-frequency noise. Code available at \url{https://github.com/yiqun-wang/PET-NeuS}.
What are some alternatives?
pytorch_geometric - Graph Neural Network Library for PyTorch
sdfstudio - A Unified Framework for Surface Reconstruction
pna - Implementation of Principal Neighbourhood Aggregation for Graph Neural Networks in PyTorch, DGL and PyTorch Geometric
DicomToMesh - A command line tool to transform a DICOM volume into a 3d surface mesh (obj, stl or ply). Several mesh processing routines can be enabled, such as mesh reduction, smoothing or cleaning. Works on Linux, OSX and Windows.
PDN - The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
smriprep - Structural MRI PREProcessing (sMRIPrep) workflows for NIPreps (NeuroImaging PREProcessing tools)
efficient-gnns - Code and resources on scalable and efficient Graph Neural Networks
giraffe - This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
graphtransformer - Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.
PolyFit - Polygonal Surface Reconstruction from Point Clouds
gnn - TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
awesome-NeRF - A curated list of awesome neural radiance fields (NeRF) papers.