Agisoft Metashape vs Nerfstudio

Agisoft Metashape processes digital images into 3D spatial data for GIS, cultural heritage documentation, visual effects, and indirect measurement. It works with aerial, close-range, and satellite imagery, including automatic camera calibration and multi-camera projects. Professional Edition can create and edit terrain and surface models, georeferenced orthomosaics, and EPSG-based outputs. Its surveying functions include aerial LiDAR point attributes, laser scan registration, ground control points, targets, and scale bars. It also handles RGB, NIR, thermal, multispectral, and satellite imagery, and can calculate user-defined indices such as NDVI. Professional Edition adds Python scripting, Java bindings, distributed calculations on a local network, and a cloud processing interface. Standard and Professional installers are available for Windows, macOS, and Linux. A 30-day full-function trial is available; demo mode blocks saving and exporting. Standard Edition costs $179, paid once, and Professional Edition costs $3,499, paid once. Regular licenses are not time-limited and include 12 months of email technical support and free updates through version 2.x.x.

Nerfstudio is a free, open-source API and toolkit for creating, training, and testing Neural Radiance Fields through modular components. Included methods are Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto, its Gaussian Splatting implementation. Command-line tools process data, train and evaluate models, render videos, view trained scenes, and export models. A web viewer shows training in real time, lets users interact with scenes, renders custom camera trajectories, and creates videos. Share URLs allow others to watch progress, but those links are publicly accessible and can add latency. Documented capture workflows use COLMAP, Polycam, or Record3D to turn phone video into a 3D render. Installation is available through pip, source, or Docker. Docker requires NVIDIA GPU drivers supporting CUDA 11.8, and the quickstart requires an NVIDIA video card with CUDA installed. The project supports Tensorboard and Wandb logging, profiling, and debugging. It runs across Linux, Windows, web, API, and self-hosted environments, with Windows described as less tested and more fragile.