# bcmi/Awesome-Image-Composition

A curated list of papers, code and resources pertaining to image composition/compositing or object/subject insertion/addition/compositing, which aims to generate realistic composite image.

Repository: https://github.com/bcmi/Awesome-Image-Composition
Canonical: https://ross.abutalabs.com/products/awesome-image-composition
License Family: other
Topics: image-composition, image-harmonization, image-blending, shadow-generation, object-placement, image-compositing, object-insertion, object-addition, object-compositing, reflection-generation, subject-addition, subject-insertion
Last push: 2026-08-20T08:35:21+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 100
- inputs: {"age_days": 1913, "days_push": 13, "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 1123, forks 95 (observed 2026-08-28T04:03:40.488540+00:00)

## What it is
A curated awesome-list of papers, datasets, code, and resources on image composition/compositing and object insertion, maintained by the BCMI lab. It organizes research by subtasks like image blending, harmonization, shadow generation, and object placement, and links to the related libcom toolbox.

## Use cases
- find papers on image harmonization
- research object insertion into background images
- find datasets for image compositing
- survey deep learning methods for realistic image composition
- find shadow generation research
- locate code for image blending tasks

## When to choose
- starting research on image composition or harmonization
- looking for datasets or benchmarks for compositing tasks
- surveying the state of the art in object insertion

## When to avoid
- you need a ready-to-use image compositing tool rather than a paper list
- you need general-purpose photo editing software
- you want production code rather than research references

## Facets
- artifact type: learning-resource
- maturity: active
- function: image-processing, machine-learning, documentation
- domain: computer-vision, image-processing, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: awesome-list, image-composition, image-harmonization, image-blending, shadow-generation, object-insertion, curated-papers, computer-vision-research

## Member repositories
- bcmi/Awesome-Image-Composition (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.488540+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 2026-08-30T06:39:53.866670+00:00, confidence not recorded.
  - readme: https://github.com/bcmi/Awesome-Image-Composition (fetched 2026-08-28T04:03:40.488540+00:00, sha 7da6247e59bf)
- Data as of 2026-08-30T08:39:29.467469+00:00.