Viso Suite vs GET3D | Nvidia

Viso Suite is an enterprise visual intelligence platform from viso.ai for building, deploying, and operating computer vision applications across cameras, sites, and industries. It connects existing camera feeds, edge devices, AI models, and business systems so operations teams can turn video into real-time alerts, dashboards, and automated workflows without stitching together separate point tools.

The platform is built around Visual General Intelligence (VGI), viso.ai's approach to scene understanding that lets teams describe what they want a camera to detect and build governed vision applications through a visual no-code studio. Viso Suite covers the full lifecycle: data collection and model training, application development, multi-site deployment, and ongoing operations with monitoring, security, and compliance controls.

Viso Suite targets complex organizations running physical operations in manufacturing, construction, transportation, retail, agriculture, healthcare, and smart city environments. Customers use it for safety monitoring, quality inspection, PPE compliance, restricted-zone alerts, crowd analytics, and other mission-critical vision use cases that need to scale across thousands of cameras and hundreds of sites.

GET3D generates textured 3D mesh assets you can drop straight into a rendering engine, trained only from collections of 2D images. NVIDIA researchers built it to output explicit meshes with geometry and texture, not neural radiance fields that need custom renderers to use.

Most 3D generative models at the time either skipped textures, locked you into fixed topology, or required neural rendering pipelines to view results. GET3D uses differentiable marching tetrahedra (DMTet) plus adversarial losses on rasterized RGB images and silhouettes, so the output is a standard textured mesh. The trade-off is research-grade access: this is an NVIDIA Toronto AI Lab project from NeurIPS 2022, not a hosted SaaS with an upload button.

The model handles cars, chairs, animals, motorbikes, human characters, and buildings. It also supports text-guided shape generation via CLIP-based finetuning, similar to StyleGAN-NADA, and can disentangle geometry from texture through separate latent codes.