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

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

A Pytree Module system for Deep Learning in JAX

Open source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.

Converting CPT to bert form for use

TensorFlowOnSpark brings TensorFlow programs to Apache Spark clusters.

Auxiliary data to the CHIIR paper Searching to Learn with Instructional Scaffolding

Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

Official PyTorch Implementation of Mask-aware IoU and maYOLACT Detector [BMVC2021]

Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"

Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.

Additional functionality for use with fastai’s medical imaging module

An 16kHz implementation of HiFi-GAN for soft-vc.

Graph Analysis From Scratch

Official implementation of the NeurIPS'21 paper 'Conditional Generation Using Polynomial Expansions'.

MMFlow is an open source optical flow toolbox based on PyTorch

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

Spatiotemporal resampling methods for mlr3

Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis in JAX

Non-Homogeneous Poisson Process Intensity Modeling and Estimation using Measure Transport