Projects sharing features with Slambook

pyslam is a framework for Simultaneous Localization and Mapping that combines Python flexibility with C++ performance. It is a sparse SLAM implementation designed to map environment geometry and track device location by processing image frames into 3D points. The project features a bridge for exposing high-performance C++ classes to Python scripts using zero-copy memory sharing. This integration allows for switching between a scripting interface for rapid prototyping and a compiled core for execution speed. The system includes a spatial map optimizer to refine 3D point and camera pose estima

COLMAP is a 3D scene reconstruction suite and C++ geometry library that implements a full structure-from-motion pipeline. It functions as a GPU-accelerated photogrammetry tool and multi-view stereo framework designed to produce dense 3D geometry and watertight meshes from collections of 2D images. The project distinguishes itself through hardware-accelerated feature extraction and a modular camera modeling system that supports perspective, fisheye, and equirectangular lens types. It employs vocabulary tree image retrieval to efficiently identify similar images in large datasets and provides P

Cartographer is a cross-platform robotics library and framework for simultaneous localization and mapping in 2D and 3D spaces. It functions as a real-time mapping engine that constructs environmental maps while tracking a device's position and orientation using continuous sensor data processing. The system implements real-time SLAM to generate precise maps for autonomous navigation. It utilizes a localization system that determines a device's state within a mapped environment across different hardware platforms and sensor configurations. The framework covers spatial estimation through non-li

This project is a comprehensive library and toolkit for simultaneous localization and mapping, designed to construct three-dimensional environment models while tracking device position. It functions as a robotics perception framework that processes data from RGB-D, stereo, and lidar sensors to enable autonomous navigation and spatial awareness. The system distinguishes itself through its focus on long-term mapping and global consistency. It employs a sophisticated loop-closure detection engine and graph-based pose optimization to identify previously visited locations and eliminate cumulative

This project is a set of exercise solutions and implementation guides for visual simultaneous localization and mapping. It provides a collection of worked code examples and mathematical solutions designed to translate theoretical localization and mapping concepts into practical implementations. The repository serves as a technical companion for academic study, featuring worked answers to SLAM exercises and a system for tracking typographical and technical corrections to maintain the accuracy of the associated written work. The codebase covers spatial mathematics and robotics geometry, includ

Ceres Solver is a C++ library for numerical optimization, specializing in non-linear least squares and unconstrained optimization problems. It serves as a framework for automatic differentiation and robust curve fitting, providing tools to solve large-scale mathematical models. The library is distinguished by its bundle adjustment capabilities, which exploit sparse matrix structures to refine 3D scene points and camera parameters. It utilizes dual-number automatic differentiation to compute derivatives of cost functions, removing the need for manual Jacobian derivation. The project covers a

LIO-SAM is a lidar inertial SLAM framework and tightly-coupled sensor fusion pipeline. It functions as a factor graph optimization engine that combines lidar scans and inertial measurement unit data to build 3D point cloud maps and estimate robot trajectories. The system integrates global position factors to align local coordinates with real-world data. It employs loop closure detection to identify previously visited locations, creating constraints in the optimization graph to correct accumulated global drift. The framework covers lidar inertial odometry, point cloud processing, and trajecto

VINS-Mono is a monocular visual-inertial odometry system and loop closure SLAM framework. It functions as a real-time state estimator that fuses data from a single camera and an inertial measurement unit to determine a robot's position and orientation. The project includes a non-linear optimizer for robotics and tools for sensor calibration. The system distinguishes itself through online sensor calibration, which automatically determines spatial extrinsics and temporal offsets between the camera and inertial unit during operation. It also incorporates rolling shutter distortion correction to

VINS-Fusion is a multi-sensor fusion framework and visual-inertial odometry system. It integrates camera images, inertial measurement unit data, and global positioning signals through a non-linear optimization system to track the position and orientation of autonomous vehicles. The system includes a visual loop closure engine that utilizes a bag-of-words approach to recognize previously visited locations and correct trajectory drift. It further provides tools for online spatio-temporal calibration to determine the physical offset and time synchronization between cameras and inertial sensors d

OpenSfM is a computer vision library and structure-from-motion pipeline designed to reconstruct three-dimensional scenes and camera trajectories from overlapping images. It functions as a 3D reconstruction engine and photogrammetry toolkit, utilizing automated feature-based image matching and incremental bundle adjustment to derive spatial geometry. The system distinguishes itself as a geospatial alignment tool, integrating GPS and inertial sensor data to align reconstructed 3D models with real-world geographic coordinates. It employs a hybrid Python and C++ execution model to manage large-sc

openMVG is a computer vision geometry library and toolkit for multiple view geometry. It serves as a framework for structure from motion and 3D scene reconstruction, providing the tools necessary to recover 3D point clouds and camera poses from collections of 2D images. The library implements both global and incremental structure-from-motion pipelines. It uses geometric algorithms to calculate camera pose estimation and image localization, employing Levenberg-Marquardt bundle adjustment to refine 3D coordinates and camera parameters by minimizing reprojection error. The project covers a broa

Cartographer is a software library and spatial localization engine for simultaneous localization and mapping. It provides a framework for calculating the precise position and orientation of a device while concurrently generating real-time 2D and 3D representations of its environment using lidar-based data. The system implements a real-time mapping approach that uses live sensor streams to track device heading and position. It utilizes a submap-based mapping strategy to divide environments into local maps that are aligned into a global map. The project covers a range of SLAM capabilities, inc

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

Open3D is a software toolkit designed for the processing, alignment, and reconstruction of three-dimensional data. It functions as a computer vision geometry engine that enables the manipulation of point clouds, meshes, and volumetric grids derived from sensor inputs. The library distinguishes itself through a high-performance computational core that executes geometric processing tasks in native code, paired with a binding layer that exposes these capabilities to high-level languages for rapid prototyping. It provides specialized algorithms for spatial registration, allowing users to merge mu

InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large reconstruction model to convert a single two-dimensional image into a three-dimensional object mesh. The system functions as a textured 3D mesh exporter, saving generated objects with either vertex colors or full texture maps for use in external rendering software. The framework covers a range of capabilities including feed-forward geometry inference, single-image depth estimation, and neural radiance fields. It also supports differentiable mesh rendering and workflows for spars

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

ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts. The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source. The toolset covers 3

TRELLIS.2 is a generative image-to-3D system that creates high-resolution 3D assets with physically based rendering materials from 2D images. It utilizes a sparse voxel representation to handle complex topologies and internal structures without relying on iso-surface fields. The project features a structured latent space representation that maps geometry and texture attributes to maintain visual fidelity. It employs an optimization-free geometry reconstruction process to decode latent representations directly into voxel grids and includes a PBR texture generator for synthesizing base color, r

vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from single two-dimensional images. It utilizes a volumetric convolutional neural network regression model to predict 3D volume data directly from image pixels. The system converts these volumetric predictions into 3D meshes through isosurface extraction and vertex coloring. It further applies realistic surface details by mapping two-dimensional image pixels onto the resulting 3D mesh using nearest-neighbor texture projection. The project provides capabilities for single-image dept

This project is a computer vision system for object segmentation and tracking across images and videos. It employs models capable of identifying and masking objects using text prompts, bounding boxes, click points, or image exemplars. The system differentiates itself through memory-based video tracking and shared-memory architectures that maintain consistent object identities over time. It supports multi-object processing in single computation passes to increase frame throughput and utilizes iterative refinement to correct segmentation boundaries through sequential prompts. The software also

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This project is a collection of neural network models and geometric tools designed for image feature matching, spatial alignment, and visual localization. It provides a pre-trained neural network model for identifying high-accuracy correspondences between sparse image features without requiring local training. The system utilizes a graph neural network matcher that employs attention mechanisms and message passing to learn spatial relationships between image feature points. It integrates a RANSAC camera pose estimator to filter feature matches and calculate the relative spatial transformation

This is the code for NIPS15 paper Weakly-supervised disentangling with recurrent transformations for 3D view synthesis by Jimei Yang, Scott Reed, Ming-Hsuan Yang and Honglak Lee.

This repository contains a tensorflow implementation for the paper "Learning Descriptor Networks for 3D Shape Synthesis and Analysis ". (http://www.stat.ucla.edu/~jxie/3DDescriptorNet/3DDescriptorNet.html)

This repository contains source code for Weakly supervised 3D Reconstruction with Adversarial Constraint. This is a fork project of our previous work, 3D-R2N2: 3D Recurrent Reconstruction Neural Network. Inspired by visual hull algorithm, we propose to learn 3D reconstruct from 2D silhouettes…

pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D image. It utilizes pixel-aligned implicit functions to map image pixels to 3D space, predicting surface occupancy and distance to create detailed geometry. The system includes a pipeline for creating digital human assets, moving from 2D image feature projection to the extraction of discrete triangular meshes. It features specialized tools for refining these models, including a post-processor that removes geometric artifacts by isolating the largest connected component of the mesh.