Skip to content

Instantly share code, notes, and snippets.

View ashishd's full-sized avatar

Ash Doshi ashishd

1 follower · 1 following
  • Curtin University
  • Perth
View GitHub Profile
@ashishd
ashishd / .block
Created April 7, 2024 10:32 — forked from steveharoz/.block
d3-force testing ground
license: gpl-3.0
height: 1030
scrolling: yes
@ashishd
ashishd / Clustering_Time_Series.ipynb
Created October 22, 2023 09:05 — forked from yassmin1/Clustering_Time_Series.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@ashishd
ashishd / pc2voxel.py
Created March 9, 2022 10:10 — forked from justanhduc/pc2voxel.py
PyTorch pointcloud to voxel
import neuralnet_pytorch as nnt
import torch as T
from torch_scatter import scatter_add
def pointcloud2voxel_fast(pc: T.Tensor, voxel_size: int, grid_size=1., filter_outlier=True):
b, n, _ = pc.shape
half_size = grid_size / 2.
valid = (pc >= -half_size) & (pc <= half_size)
valid = T.all(valid, 2)
@ashishd
ashishd / SFM.md
Created June 15, 2021 02:57 — forked from patriciogonzalezvivo/SFM.md
SfM Tools

VisualSFM by Changchang Wu

Probably the most straight forward way to start generating Point Clouds from a set of pictures.

VisualSFM is a GUI application for 3D reconstruction using structure from motion (SFM). The reconstruction system integrates several of my previous projects: SIFT on GPU(SiftGPU), Multicore Bundle Adjustment, and Towards Linear-time Incremental Structure from Motion. VisualSFM runs fast by exploiting multicore parallelism for feature detection, feature matching, and bundle adjustment.

For dense reconstruction, this program supports Yasutaka Furukawa's PMVS/CMVS tool chain, and can prepare data for Michal Jancosek's CMP-MVS. In addition, the output of VisualSFM is natively supported by Mathias Rothermel and Konrad Wenzel's [SURE]