179 Open source projects that are alternatives of or similar to 3DShapeGen

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

This project is to convert PortraitFCN+ (by Xiaoyong Shen) from Matlab to Tensorflow, then refine the outputs from it (converted to a trimap) using KNN and ResNet, supervised by Richard Berwick.

Adaptive Surface Reconstruction for 3D Data Processing

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

List of projects for 3d reconstruction

Collecting papers about new view synthesis

A readable implementation of structure-from-motion

Official repository for the ShapeFormer Project

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image

Simple (but often Strong) Baselines for POMDPs in PyTorch - ICML 2022

Deep Single-View 3D Object Reconstruction with Visual Hull Embedding

Code for Learnt Stereo Machines based on the NIPS 2017 paper

[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"

[cvpr19] Hands+Objects synthetic dataset, instructions to download and code to load the dataset

MVSNet: Depth Inference for Unstructured Multi-view Stereo using pytorch-lightning

Automatically registers (aligns) and visualizes point clouds, or processes a whole bunch at once

Semantic-TSDF for Self-driving Static Scene Reconstruction

The detection of peaks and valleys in a 1d-vector or 2d-array (image)

[CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Graduation Project: A point cloud semantic segmentation and VIO based 3D reconstruction method using RGB-D and IMU

An application displaying 2D/3D Dicom

Motion Averaging

Creating a 3D reconstruction of an object using multiple images

A list of papers and datasets about point cloud analysis (processing)

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV2020)

[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Computing various norms/measures on over-parametrized neural networks

Visual Odometry with Inertial and Depth (VOID) dataset

This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"

Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

Official repository for the paper "Learning Local Neighboring Structure for Robust 3D Shape Representation"

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

CVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"

The 3D Public Transport Simulator is a Unity-based simulation, which uses OpenStreetMap data in order to support the simulation of worldwide locations. The development was part of a Bachelor thesis.

ML/DL/RL paper notes

A Collection of Algorithms for Relative Pose Estimation of a Calibrated Camera

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

[3DV 2021] DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

Global L0 algorithm for regularity-constrained plane fitting

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning

A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm

API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset

a 3D-Reconstruction demo done with Kinect

This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

Code and Data Release for GenRe (NeurIPS 2018) and ShapeHD (ECCV 2018)

Implementation of the paper Recurrent Independent Mechanisms (https://arxiv.org/pdf/1909.10893.pdf)

Code for PCN: Point Completion Network in 3DV'18 (Oral)

SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification - ECCV 2020 oral

This repository contains the source codes for the paper "DmifNet: 3D Shape Reconstruction based on Dynamic Multi–Branch Information Fusion (ICPR 2020 Oral)"

Demonstration of different algorithms and operations on faces. Join the Discord channel for discussion.

[WACV 2021] Dynamic Plane Convolutional Occupancy Networks

generalize counter-examples of property-based testing

Implementation for paper "Learning Single-View 3D Reconstruction with Limited Pose Supervision".

Escaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]