KIRI Engine vs Nerfstudio

KIRI Engine is a 3D scanning application that creates models and visualizations using photogrammetry, Neural Surface Reconstruction, and 3D Gaussian Splatting. Photo Scan creates 3D models from photos. LiDAR Scan supports model scans, floor plans, and quick scene visualizations on LiDAR-equipped iOS devices, while Featureless Object Scan is designed for shiny, reflective, transparent, and low-texture objects. The free Basic plan costs nothing and permits up to 150 photos and 2 GB per scan, with unlimited scans and free exports. Pro costs $17.99 a month or $79.99 a year, and raises the limits to 500 photos and 5 GB per scan while adding faster queue processing and advanced scanning and modeling features. The API offers Photo Scan, Featureless Scan, and 3DGS Scan; each API call uses one credit. Credits cost 1.00 USD each, with a 500-credit minimum recharge and 10 free test credits at sign-up. Other listed tools include a website model embedder, a UE5 plug-in, and STL export. Uploaded photos and videos are processed on cloud servers, and local PC scanning is not on the company's roadmap at the moment.

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.