# apple/ml-hypersim

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Repository: https://github.com/apple/ml-hypersim
Canonical: https://ross.abutalabs.com/products/ml-hypersim
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-01-09T22:34:45+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 61, release rhythm 35, longevity 100
- inputs: {"age_days": 2116, "days_push": 236, "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 2043, forks 153 (observed 2026-08-28T04:06:08.610809+00:00)

## What it is
Hypersim is a photorealistic synthetic dataset of 74,619 images across 461 indoor scenes with dense per-pixel semantic instance segmentation labels and ground truth geometry. It also includes a toolkit for generating such images from publicly available 3D assets.

## Use cases
- train semantic segmentation models for indoor scenes
- get per-pixel ground truth labels unavailable from real images
- train depth estimation or surface normal prediction models
- research intrinsic image decomposition into reflectance and illumination
- benchmark holistic indoor scene understanding models
- generate custom synthetic training images from 3D assets

## When to choose
- you need dense per-pixel ground truth labels for indoor scene understanding
- you want complete scene geometry, material, and lighting information
- you need large-scale photorealistic training data with camera parameters
- you want to study view-dependent lighting effects via decomposed image components

## When to avoid
- you need real-world photographic data rather than synthetic renders
- you cannot store roughly 1.9TB of image data
- your task involves outdoor scenes or people (people images were excluded)
- you need a small, lightweight dataset for quick experiments

## Facets
- artifact type: dataset
- maturity: stable
- function: data-generation, image-processing, computer-vision, machine-learning
- domain: computer-vision, image-processing, machine-learning, artificial-intelligence, simulation
- platform: python, windows
- tags: synthetic-data, scene-understanding, semantic-segmentation, depth-estimation, indoor-scenes, photorealistic-rendering, per-pixel-labels, 3d-assets, linux, macos

## Member repositories
- apple/ml-hypersim (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.610809+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 2026-08-30T02:58:06.610176+00:00, confidence not recorded.
  - readme: https://github.com/apple/ml-hypersim (fetched 2026-08-28T04:06:08.610809+00:00, sha 6df13b413d10)
- Data as of 2026-08-30T08:39:29.467469+00:00.