Nerfstudio vs WebODM

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.

WebODM turns aerial images into georeferenced maps, point clouds, digital elevation models, textured 3D models, and Gaussian splats. It accepts photos or videos from any drone, including JPG, TIFF, video files, and multispectral imagery, and can run on a user's computer while offline. Exports include GeoTIFF, PNG, LAS/LAZ, OBJ, and OGC 3D Tiles. Mapping tools cover measurements, plant-health indexes, ground-control points, elevation contours, rolling-shutter correction, and sharing links. WebODM uses ODX, a free, open-source photogrammetry engine that developers can run from the command line or integrate into software. It can also connect to processing nodes that speak the NodeODX API. The API uses token authentication through the /api/token-auth/ endpoint, with tokens expiring after six hours by default. Model-level and row-level permissions govern whether users can view, add, edit, or delete objects. WebODM is free to install and use locally; optional cloud plans are listed at $24 a month billed yearly for Starter, $35 a month billed yearly for Pro, and $99 a month billed yearly for Business. Minimum requirements are 8 GB RAM and 20 GB disk space; larger datasets have higher recommended requirements.