RTAB vs Rosettica

RTAB-Map (Real-Time Appearance-Based Mapping) is an Open Source LiDAR / RGB-D / Stereo Graph-Based SLAM (Simultaneous Localization and Mapping) approach based on an online incremental appearance-based loop closure detector. The loop closure detector uses a bag-of-words approach to determinate how likely a new image comes from a previous location or a new location. When a loop closure hypothesis is accepted, a new constraint is added to the map's graph, then a graph optimizer minimizes the errors in the map in real-time. An optional memory management approach can be used to limit the number of locations used for loop closure detection and graph optimization, so that real-time constraints on large-scale environnements are always respected. ARKit's visual inertial odometry (VIO) is used as the SLAM front-end for RTAB-Map (the SLAM back-end). * Note that unlike other scanning apps that optimize the map only after mapping, with RTAB-Map you get loop closure detection and map optimization online so you can have a live feedback to know when you have enough constraints in the map for good global optimization before stopping the scan. *** 3D reconstruction available only with LiDAR sensor. Features: * Online 3D scanning/mapping of the environment. * Online loop closure detection and map correction. * Save in DB format (RTAB-Map desktop and rtabmap_ros format). * Export in PLY, LAS or OBJ. * Multi-session mapping (save and continue later). * Use Apriltags to help finding loop closures in textureless environments. * Mixed AR/VR First-Person in visualization mode. * Raw ARKit data recording (up to 60 Hz!), useful to record long sessions without comprising battery life.

One input. Many languages. Rosettica helps you translate text into several languages on iPhone, iPad and Mac. Choose where translation happens: on your device, on a nearby Mac, or on a translation server you configure. TRANSLATE YOUR WAY Choose your source language or use automatic detection. Select several target languages and save combinations for work, study or everyday use. Follow each language's progress, stop a task, retry a failed translation and keep results that have already finished. START WITH TEXT, PHOTOS OR FILES Paste text, import text and image files, or extract text from photos. On iPhone and iPad, capture text with the camera and review the recognized words before translating. Send text from other apps to Rosettica, then review it in the app. KEEP YOUR WORK ORGANIZED Search translation history, mark favorites and reuse earlier inputs. Copy, export and share completed results. Add glossary terms to specify preferred translations for exact phrases. Optional iCloud backup lets you back up and restore your history. A WORKSPACE FOR EACH DEVICE Use a touch-friendly layout on iPhone and iPad. On Mac, work with source text and translations side by side, keep your main actions within reach and expand the editor when you need more room. SPEAK AND LISTEN Use speech recognition, translation and system voices in conversation mode. Speech recognition may require an internet connection, and available languages and voices depend on your device and Apple services. CHOOSE WHERE YOUR TEXT GOES On-device text translation runs locally after the required model has been downloaded and prepared on a compatible device. Nearby-Mac mode sends text to the Mac you pair with on your local network. Remote mode sends text to the server you select; its operator determines processing and retention. The app identifies the selected processing location so you can choose the workflow that suits your content. On-device translation requires a compatible device, an initial model download and sufficient free storage. Rosettica checks readiness before preparation. Camera input is available on iPhone and iPad. Network-based translation requires an available Mac or configured server; translation quality depends on the selected model and language.