Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Last update: Dec 12, 2022

Overview

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors (CVPR 2022)

Personal Web Pages | Paper | Project Page

This repository contains the code to reproduce the results from the paper. [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://arxiv.org/abs/2204.11015).

You can find detailed usage instructions for training your own models and using pretrained models below.

If you find our code or paper useful, please consider citing

@inproceedings{PredictiveContextPriors,
    title = {Surface Reconstruction from Point Clouds by Learning Predictive Context Priors},
    author = {Baorui, Ma and Yu-Shen, Liu and Matthias, Zwicker and Zhizhong, Han},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2022}
}

Surface Reconstruction Demo

Predicted Queries Visualization

Predicted queries in Loccal Coorinate System

Installation

First you have to make sure that you have all dependencies in place. The simplest way to do so, is to use anaconda.

You can create an anaconda environment called tf using

conda env create -f tf.yaml
conda activate tf

Training

You should train the Local Context Prior Network first, run

python pcp.py --input_ply_file test.ply --data_dir ./data/ --CUDA 0 --OUTPUT_DIR_LOCAL ./local_net/ --OUTPUT_DIR_GLOBAL ./glocal_net/ --train --save_idx -1

You should put the point cloud file(--input_ply_file, only ply format) into the '--data_dir' folder.

Then train the Predictive Context Prior Network, run

python pcp.py --input_ply_file test.ply --data_dir ./data/ --CUDA 0 --OUTPUT_DIR_LOCAL ./local_net/ --OUTPUT_DIR_GLOBAL ./glocal_net/ --finetune --save_idx -1

Test

You can extract the mesh model from the trained network, run

python pcp.py --input_ply_file test.ply --data_dir ./data/ --CUDA 0 --OUTPUT_DIR_LOCAL ./local_net/ --OUTPUT_DIR_GLOBAL ./glocal_net/ --test --save_idx -1

Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Related tags

Overview

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors (CVPR 2022)

Personal Web Pages | Paper | Project Page

Surface Reconstruction Demo

Predicted Queries Visualization

Predicted queries in Loccal Coorinate System

Installation

Training

Test

Owner

A simple python module to generate anchor (aka default/prior) boxes for object detection tasks.

This repo includes the CUB-GHA (Gaze-based Human Attention) dataset and code of the paper "Human Attention in Fine-grained Classification".

A super lightweight Lagrangian model for calculating millions of trajectories using ERA5 data

【steal piano】GitHub偷情分析工具！

A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers.

JudeasRx - graphical app for doing personalized causal medicine using the methods invented by Judea Pearl et al.

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

MetaTTE: a Meta-Learning Based Travel Time Estimation Model for Multi-city Scenarios

Training Structured Neural Networks Through Manifold Identification and Variance Reduction

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

Minimal deep learning library written from scratch in Python, using NumPy/CuPy.

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Train DeepLab for Semantic Image Segmentation

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

A python package simulating the quasi-2D pseudospin-1/2 Gross-Pitaevskii equation with NVIDIA GPU acceleration.

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

Fastshap: A fast, approximate shap kernel

This repository is an unoffical PyTorch implementation of Medical segmentation in 3D and 2D.