A blender add-on that automatically re-aligns wrong axis objects.

Overview

Auto Align

A blender add-on that automatically re-aligns wrong axis objects.

inform

Usage

There are three options available in the 3D Viewport > Sidebar > Item > Auto Align.

  • Rotate : Rotate the selected object to match the world axis.
  • Rotate & Bake : Same as Rotate, but rotation is applied.
  • Keep Position & Bake : Keep the object fixed and only change the local axis.

Also there is a symmetry option. This option can be used to align symmetrical objects, even though there are not many orthogonal faces to the axis. It's a bit slower, but effective when aligning organic objects, such as people.

inform2

Note

  • The object should be symmetric or have enough orthogonal faces.
  • When using symmetry option, the model doesn't need to be completely symmetrical because the algorithm considers the outlier.
  • The symmetry plane detection algorithm is far from perfect. If the object is complex (>105 vertices?), symmetry detection will fail with a high probability. Also, if a single object has multiple planes of symmetry, the alignment can be done in an unintended manner.

Algorithm

Orientation

The proper orientation of the object is calculated as follows:

  1. RANSAC (Random sample consensus)

    • Randomly select two orthogonal faces to create a candidate orientation.
    • Find the faces that corresponding to the axis within a specific threshold (<5 deg).
    • Criterion is to maximize the sum of the areas of the face.
  2. Correction

    • Fine-tune the candidate orientation.
    • Find the weighted median of the points on each axis and rotate the orientation.
    • Repeat until convergence.
  3. XYZ adjustment

    • To avoid continuous flips and maintain consistency while repeating the same operation.
    • Determine XYZ axis to have the least difference from the initial mesh orientation.

For each object, only up to 104 faces are considered in the process. This is due to performance reason. If there are more than 104 faces, larger faces would be considered first.

Symmetry Plane Detection

When the symmetry option is on, the symmetry plane must be derived before RANSAC.

  1. Vertex pair matching
    • Randomly extract vertex pairs that satisfy symmetry conditions.
    • Vertex normals must be consistent with their relative positions.
  2. Plane voting
    • 4 parameters of fitting plane is calculated from each pair.
    • From 4D voting space, choose plane parameters that receive the most votes.
  3. Correction
    • From the planes within a certain distance, calculate the median of each parameter.
SimulLR - PyTorch Implementation of SimulLR

PyTorch Implementation of SimulLR There is an interesting work[1] about simultan

11 Dec 22, 2022
[Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021

Convolutional MLP ConvMLP: Hierarchical Convolutional MLPs for Vision Preprint link: ConvMLP: Hierarchical Convolutional MLPs for Vision By Jiachen Li

SHI Lab 143 Jan 03, 2023
[CVPR 2022 Oral] TubeDETR: Spatio-Temporal Video Grounding with Transformers

TubeDETR: Spatio-Temporal Video Grounding with Transformers Website • STVG Demo • Paper This repository provides the code for our paper. This includes

Antoine Yang 108 Dec 27, 2022
Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image

CenterPose Overview This repository is the official implementation of the paper "Single-stage Keypoint-based Category-level Object Pose Estimation fro

NVIDIA Research Projects 188 Dec 27, 2022
Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

Codes for ECBSR Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices Xindong Zhang, Hui Zeng, Lei Zhang ACM Multimedia 202

xindong zhang 236 Dec 26, 2022
Implementation of U-Net and SegNet for building segmentation

Specialized project Created by Katrine Nguyen and Martin Wangen-Eriksen as a part of our specialized project at Norwegian University of Science and Te

Martin.w-e 3 Dec 07, 2022
Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision Training Efficiency We show the training efficiency of our DSLP model b

Chenyang Huang 36 Oct 31, 2022
Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection PyTorch code release of the paper "Attentive Prototypes for Sour

Deepti Hegde 23 Oct 17, 2022
The Unsupervised Reinforcement Learning Benchmark (URLB)

The Unsupervised Reinforcement Learning Benchmark (URLB) URLB provides a set of leading algorithms for unsupervised reinforcement learning where agent

259 Dec 26, 2022
Official implementation of ACMMM'20 paper 'Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework'

Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework Official code for paper, Self-supervised Video Representation Le

Li Tao 103 Dec 21, 2022
Explainability for Vision Transformers (in PyTorch)

Explainability for Vision Transformers (in PyTorch) This repository implements methods for explainability in Vision Transformers

Jacob Gildenblat 442 Jan 04, 2023
mmdetection version of TinyBenchmark.

introduction This project is an mmdetection version of TinyBenchmark. TODO list: add TinyPerson dataset and evaluation add crop and merge for image du

34 Aug 27, 2022
Instant Real-Time Example-Based Style Transfer to Facial Videos

FaceBlit: Instant Real-Time Example-Based Style Transfer to Facial Videos The official implementation of FaceBlit: Instant Real-Time Example-Based Sty

Aneta Texler 131 Dec 19, 2022
Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks

Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks This is the official code for DyReg model inroduced in Discovering Dyna

Bitdefender Machine Learning 11 Nov 08, 2022
MDMM - Learning multi-domain multi-modality I2I translation

Multi-Domain Multi-Modality I2I translation Pytorch implementation of multi-modality I2I translation for multi-domains. The project is an extension to

Hsin-Ying Lee 107 Nov 04, 2022
AI grand challenge 2020 Repo (Speech Recognition Track)

KorBERT를 활용한 한국어 텍스트 기반 위협 상황인지(2020 인공지능 그랜드 챌린지) 본 프로젝트는 ETRI에서 제공된 한국어 korBERT 모델을 활용하여 폭력 기반 한국어 텍스트를 분류하는 다양한 분류 모델들을 제공합니다. 본 개발자들이 참여한 2020 인공지

Young-Seok Choi 23 Jan 25, 2022
《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)

A-CNN: Annularly Convolutional Neural Networks on Point Clouds Created by Artem Komarichev, Zichun Zhong, Jing Hua from Department of Computer Science

Artёm Komarichev 44 Feb 24, 2022
FTIR-Deep Learning - FTIR Deep Learning With Python

CANDIY-spectrum Human analyis of chemical spectra such as Mass Spectra (MS), Inf

Wei Mei 1 Jan 03, 2022
Self-supervised learning algorithms provide a way to train Deep Neural Networks in an unsupervised way using contrastive losses

Self-supervised learning Self-supervised learning algorithms provide a way to train Deep Neural Networks in an unsupervised way using contrastive loss

Arijit Das 2 Mar 26, 2022
Dual Attention Network for Scene Segmentation (CVPR2019)

Dual Attention Network for Scene Segmentation(CVPR2019) Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu Introduction W

Jun Fu 2.2k Dec 28, 2022