114 Open source projects that are alternatives of or similar to pais-mvs

Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence, CVPR 2019

Code for: "Learning To Adapt For Stereo" accepted at CVPR2019

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

Reconstructing real-time 3D faces from 2D images using deep learning.

Pytorch implementation for stereo matching described in the paper: Efficient Deep learning for stereo matching

Smart filter to remove Floyd-Steinberg dithering from paletted images

A repository for the paper "Improved Adversarial Systems for 3D Object Generation and Reconstruction".

Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)

An official pyTorch port of the pix2vertex paper from ICCV2017

Awesome GAN for Medical Imaging

Code for "Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation"

CarveMe: genome-scale metabolic model reconstruction

The consensus GEM for Saccharomyces cerevisiae

official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"

ROS wrapper for Kimera-VIO

Tensorflow Implementation of Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (NAACL 2019).

An integrated SfM (Structure from Motion) and MVS (Multi-View Stereo) solution.

Deep Image Compression using Decoder Side Information (ECCV 2020)

Comparative Evaluation of Hand-Crafted and Learned Local Features

A Julia project demonstrating the fast f-k migration algorithm.

[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

MOTSFusion: Track to Reconstruct and Reconstruct to Track

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

UAV-Mapper is a lightweight UAV Image Processing System, Visual SFM reconstruction or Aerial Triangulation, Fast Ortho-Mosaic, Plannar Mosaic, Fast Digital Surface Map (DSM) and 3d reconstruction for UAVs.

Real-time dense visual SLAM system

The old implementation of GraphSfM based on openMVG.

TREES toolbox

A C++ tool for 3D reconstruction from parallel 2D sections

Tensorflow implementation(unofficial) of "Digging into Self-Supervised Monocular Depth Prediction"

C++ simulation, reconstruction and analysis framework for particle physics experiments

Semi-Global Matching

Dual CNN Models for Unsupervised Monocular Depth Estimation

A multi-sensor capture system for free viewpoint video.

DSGN: Deep Stereo Geometry Network for 3D Object Detection (CVPR 2020)

Tomographic Reconstruction in Python

Perform stereo matching algorithm using Direct 3D (level 9.3) on a mobile device without CUDA support.

Track Advancement of SLAM 跟踪SLAM前沿动态【2021 version】

[CVPR 2020] Normal Assisted Stereo Depth Estimation

A structured light scanner

DIODE Development Toolkit

The COnstraint-Based Reconstruction and Analysis Toolbox. Documentation:

[CVPR'21] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

[CVPR 2017] Generation and reconstruction of 3D shapes via modeling multi-view depth maps or silhouettes

Self-Supervised Depth Estimation on Monocular Sequences

Python package for signal processing, with emphasis on iterative methods

The Light Dark Matter eXperiment simulation and reconstruction framework.

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

Official Code: 3D Scene Reconstruction from a Single Viewport

A program for controlling a micro-UAV for obstacle detection and collision avoidance using disparity mapping

📚 The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

Restoring room images from virtual background images

Blender importer of meshroom datafiles: cameras, images, sparse pointcloud and obj's.

A curated list of awesome Single-view 3D Object Reconstruction papers & resources

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.

A high-level, easy-to-deploy non-uniform Fast Fourier Transform in PyTorch.

The PatchMatch stereo match algorithm implemented by CUDA.

gc-net for stereo matching by using pytorch

MXNET/Gluon Implementation of End-to-end 3D Face Reconstruction with Deep Neural Networks