Datasets › AIM-500

AIM-500 (Automatic Image Matting-500)

Introduced by Jizhizi Li et al. in Deep Automatic Natural Image Matting15 Jul 2021 archive 2025-07-28

AIM-500 is the first natural image matting test set, contains 500 high-resolution real-world natural images from three types of images (salient opaque foregrounds, salient transparent/meticulous foregrounds, non-salient foregrounds), and multiple categories. The amount of each category is shown in the following table.

Portrait Animal Transparent Plant Furniture Toy Fruit
100 200 34 75 45 36 10

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Matting AIM-500 DiffMatte SAD 16.31 Diffusion for Natural Image Matting yihanhu-2022/diffmatte 6 Compare

Papers archive 2025-07-28

6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 23. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Diffusion for Natural Image Matting 1 1 10 Dec 2023 ran 6 of 7 samples (1 unverified; 7 pointer-only for licence)
Deep Automatic Natural Image Matting 1 1 15 Jul 2021 ran 2 of 3 samples (1 unverified)
Bridging Composite and Real: Towards End-to-end Deep Image Matting 1 1 30 Oct 2020 ran 3 of 3 samples (0 unverified; 1 pointer-only for licence)
A Late Fusion CNN for Digital Matting 1 1 1 Jun 2019 not harvested
U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans 0 1 23 Jan 2019 not harvested
Semantic Human Matting 2 1 5 Sep 2018 not harvested

Dataset loaders archive 2025-07-28

JizhiziLi/AIMtfpytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • AIM-500

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections