# apple/ml-sharp

Sharp Monocular View Synthesis in Less Than a Second

Repository: https://github.com/apple/ml-sharp
Canonical: https://ross.abutalabs.com/products/ml-sharp
Homepage: https://apple.github.io/ml-sharp/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-12-19T05:14:10+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 35, longevity 18
- inputs: {"age_days": 264, "days_push": 257, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8843, forks 647 (observed 2026-08-28T04:10:25.999573+00:00)

## What it is
SHARP is a Python tool from Apple that synthesizes a photorealistic 3D Gaussian splat representation from a single photograph in under a second via a feedforward neural network. The resulting metric 3DGS scenes can be rendered in real time for nearby camera views and exported as standard .ply files compatible with common 3DGS renderers.

## Use cases
- turn a single photo into a 3D gaussian splat scene
- generate novel views from one image
- render camera trajectory videos from a photograph
- export 3DGS ply files for external splat renderers
- fast single-image 3D reconstruction with metric scale

## When to choose
- you need fast photorealistic view synthesis from a single image
- you want metric-scale 3D Gaussian splats without per-scene optimization
- you need 3DGS output compatible with existing splat renderers

## When to avoid
- you need full 360-degree scene reconstruction from multiple views
- you have no GPU and need video rendering
- you require a permissively licensed library for commercial redistribution without review

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, computer-vision, graphics, cli
- domain: computer-vision, graphics, machine-learning, artificial-intelligence
- platform: python, cli
- tags: view-synthesis, 3d-gaussian-splatting, monocular-depth, novel-view-synthesis, neural-rendering, single-image-3d, gpu, linux, macos

## Member repositories
- apple/ml-sharp (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:25.999573+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 2026-08-29T17:24:48.428387+00:00, confidence not recorded.
  - readme: https://github.com/apple/ml-sharp (fetched 2026-08-28T04:10:25.999573+00:00, sha 1bcafa5bc9de)
  - homepage: https://apple.github.io/ml-sharp/ (fetched 2026-08-29T08:25:09.760015+00:00, sha 26bb6c84f74b)
- Data as of 2026-08-30T08:39:29.467469+00:00.