# nv-tlabs/vipe

ViPE: Video Pose Engine for Geometric 3D Perception

Repository: https://github.com/nv-tlabs/vipe
Canonical: https://ross.abutalabs.com/products/vipe
Homepage: https://research.nvidia.com/labs/toronto-ai/vipe
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d, camera, depth-estimation, slam
Last push: 2026-08-17T23:14:20+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 87, longevity 27
- inputs: {"age_days": 388, "days_push": 16, "days_rel": 85, "gap_med": 12.0, "n_releases_24m": 3}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2092, forks 170 (observed 2026-08-28T04:06:12.453776+00:00)

## What it is
ViPE is an open-source video processing engine from NVIDIA that estimates camera intrinsics, camera motion, and dense near-metric depth maps from unconstrained raw videos. It supports pinhole, wide-angle, and 360-degree panorama footage and combines SLAM-style bundle adjustment with monocular depth networks.

## Use cases
- annotate camera poses and depth maps from raw videos
- estimate camera intrinsics and motion from selfie or dashcam footage
- generate 3D annotations for spatial AI training data
- process 360-degree panorama videos for 3D reconstruction
- run SLAM-style pose estimation on unconstrained video
- recover metric depth from monocular video

## When to choose
- you need automated 3D annotations (poses, intrinsics, depth) from in-the-wild videos
- you work with diverse camera models including wide-angle and panoramas
- you want a GPU-accelerated pipeline with CUDA optimizations
- you are building spatial AI or robotics datasets from video

## When to avoid
- you need real-time on-device SLAM on embedded hardware
- your videos are static images rather than video sequences
- you require a permissively licensed codebase without non-commercial components (Unik3D part is BY-NC-SA 4.0)
- you need a lightweight CPU-only tool

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, video-processing, gpu-computing
- domain: computer-vision, robotics, artificial-intelligence
- platform: python, cli
- tags: slam, camera-pose-estimation, depth-estimation, 3d-perception, spatial-ai, nvidia, bundle-adjustment, panorama, video-annotation, video, linux, gpu

## Member repositories
- nv-tlabs/vipe (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:12.453776+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:55:30.790571+00:00, confidence not recorded.
  - readme: https://github.com/nv-tlabs/vipe (fetched 2026-08-28T04:06:12.453776+00:00, sha 996b3703b0f9)
  - homepage: https://research.nvidia.com/labs/toronto-ai/vipe (fetched 2026-08-29T10:35:14.034362+00:00, sha 659e23cd3356)
- Data as of 2026-08-30T08:39:29.467469+00:00.