Awesome GitHub RepositoriesPoint Cloud Reconstruction

This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language descriptions or two-dimensional images into three-dimensional assets using neural radiance fields and diffusion models. The system utilizes score-distillation sampling and diffusion-based guidance to refine 3D shapes without requiring 3D training data. It includes specialized tools for transforming neural representations into exportable meshes with texture and material data, as well as a pipeline for iterative optimization of geometry and textures. The project covers a broad r

Draco is a library and toolset for compressing, transcoding, and decoding 3D geometric meshes and point cloud data. Its primary purpose is to reduce storage size and transmission bandwidth for 3D assets. The project includes a geometry optimizer specifically for glTF file containers to reduce asset footprints. It also features a hardened decoder designed to process malformed or untrusted 3D geometric data safely to prevent memory corruption and crashes. The software covers a broad range of 3D data processing capabilities, including geometric data reconstruction, point attribute management, a

Point-e is a system for 3D model synthesis that generates three-dimensional point clouds from natural language descriptions and two-dimensional images. It utilizes diffusion models to synthesize these spatial representations based on text prompts or source images. The project includes specialized tools for refining these outputs, such as a point cloud upsampler to increase the density and resolution of low-resolution models. It also provides a mesh converter that uses distance function regression to transform raw point cloud data into structured 3D meshes. The broader capability surface cove

Kaolin एक PyTorch 3D डीप लर्निंग लाइब्रेरी है जो 3D ज्यामिति प्रसंस्करण, भौतिकी सिमुलेशन, डेटा विज़ुअलाइज़ेशन, और कंप्यूटर विज़न के लिए ग्रेडिएंट-आधारित रेंडरिंग के लिए टूल का एक व्यापक सूट प्रदान करती है। इस लाइब्रेरी में एक डिफरेंशिएबल 3D रेंडरर और मेश और पॉइंट क्लाउड जैसे 3D अभ्यावेदन को बदलने और बदलने के लिए एक ज्यामिति प्रसंस्करण टूलकिट शामिल है। इसमें त्रि-आयामी वस्तुओं और दृश्यों के बीच भौतिक इंटरैक्शन और टकराव की गणना करने के लिए एक 3D भौतिकी सिमुलेशन इंजन भी है। यह टूलकिट 3D डेटा विज़ुअलाइज़ेशन के लिए यूटिलिटीज प्रदान करती है, जिसमें इंटरैक्टिव दृश्य और टर्नटेबल एनिमेशन का निर्माण शामिल है। अतिरिक्त क्षमताएं 3D डेटासेट प्रबंधन, डेटा प्रीप्रोसेसिंग, और 3D अभ्यावेदन रेंडरिंग को कवर करती हैं।

GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and tetrahedral meshes. It functions as an image-to-3D reconstructor and text-to-3D generator, utilizing a differentiable 3D renderer to produce realistic visual perspectives and material effects. The system enables the creation of 3D assets from single 2D images, point clouds, or descriptive text prompts. It features a latent space interpolator for creating smooth transitions between different 3D objects and supports the independent control of geometry and texture. The project cov

openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

Please see our follow-up work PPSurf. It's easier to use, much faster and better.

Implicit Geometric Regularization for Learning Shapes

by: Alexandre Boulch and Renaud Marlet

Paper - Supplementaty - Project Website - Arxiv - Published in NeurIPS 2020.

Personal Web Pages | Paper | Project Page

This repository contains the code to reproduce the results from the paper.

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.

This repository contains the implementation of our papers Dual Octree Graph Networks. The experiments are conducted on Ubuntu 18.04 with 4 V400 GPUs (32GB memory). The code is released under the MIT license.

The reference implementaiton for the CVPR 2019 paper Deep Geometric Prior for Surface Reconstruction.

This repository contains the implementation of the paper:

` pytorch #1.10.0+cu111 pytorch3d #0.6.2 open3d trimesh point-cloud-utils cd pointnet2opslib python setup.py install Download the data from Google Drive (These shapes are processed by DISN, remove the interior and non-manifold structures.) Then use the codes in scripts to get the dataset.…

Project Page | Personal Web Page | Paper

Source code & pretrained model for "PointTriNet: Learned Triangulation of 3D Point Sets", by Nicholas Sharp and Maks Ovsjanikov at ECCV 2020.

This is our implementation of the paper Differentiable Surface Triangulation that enables optimization for any per-vertex or per-face differentiable objective function over the space of underlying surface triangulations.