NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running inference for a TAO NVPanoptix3D model.
Install
npx skills add NVIDIA/skills --skill tao-train-nvpanoptix3dnpx skills add NVIDIA/skills --skill tao-train-nvpanoptix3d -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-nvpanoptix3d -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-nvpanoptix3dgh skill install NVIDIA/skills tao-train-nvpanoptix3dgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-train-nvpanoptix3d ~/.claude/skills/tao-train-nvpanoptix3d # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-nvpanoptix3d ~/.agents/skills/tao-train-nvpanoptix3d # Codex, Cursor, Gemini CLI, Copilot, OpenCode