Image Matting

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 110 papers with code (225 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
  24 May 2023 9 repositories listed
  Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining.
• MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
  24 Nov 2020 9 repositories listed
  MODNet is easy to be trained in an end-to-end manner.
• Deep Image Matting
  10 Mar 2017 8 repositories listed Syntology ran 2 of 14 samples · 12 unverified · 2 pointer-only (licence)
  We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
• Index Network
  11 Aug 2019 6 repositories listed
  By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data…
• Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
  20 Nov 2019 5 repositories listed
  With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.
• Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
  22 Oct 2020 4 repositories listed
  This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles.
• Intra-frame Object Tracking by Deblatting
  9 May 2019 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object.
• TOM-Net: Learning Transparent Object Matting from a Single Image
  13 Mar 2018 3 repositories listed
  In this paper, we first formulate transparent object matting as a refractive flow estimation problem.
• ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning
  30 Dec 2024 2 repositories listed
  To solve this, we present ReFlow6D, a novel method for transparent object 6D pose estimation that harnesses the refractive-intermediate representation.
• Alfie: Democratising RGBA Image Generation With No $$$
  27 Aug 2024 2 repositories listed
  Designs and artworks are ubiquitous across various creative fields, requiring graphic design skills and dedicated software to create compositions that include many graphical elements, such as logos, icons, symbols, and…
• On Point Affiliation in Feature Upsampling
  17 Jul 2023 2 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 5 pointer-only (licence)
  We introduce the notion of point affiliation into feature upsampling.
• SAPA: Similarity-Aware Point Affiliation for Feature Upsampling
  26 Sep 2022 2 repositories listed
  We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity.
• Deep PCB To COCO Convertor
  1 May 2022 2 repositories listed
  It has 1500 image pairs.
• Privacy-Preserving Portrait Matting
  29 Apr 2021 2 repositories listed Syntology ran 5 of 15 samples · 10 unverified
  We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization capabilities when following the Privacy-Preserving Training…
• Real-Time High-Resolution Background Matting
  14 Dec 2020 2 repositories listed
  We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU.
• Fast Multi-Level Foreground Estimation
  26 Jun 2020 2 repositories listed
  Alpha matting aims to estimate the translucency of an object in a given image.
• Camouflaged Object Detection
  1 Jun 2020 2 repositories listed
  We present a comprehensive study on a new task named camouflaged object detection (COD), which aims to identify objects that are "seamlessly" embedded in their surroundings.
• F, B, Alpha Matting
  17 Mar 2020 2 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  Cutting out an object and estimating its opacity mask, known as image matting, is a key task in many image editing applications.
• Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects
  25 Nov 2019 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified · 3 pointer-only (licence)
  We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a…
• Non-Causal Tracking by Deblatting
  15 Sep 2019 2 repositories listed
  Tracking by Deblatting stands for solving an inverse problem of deblurring and image matting for tracking motion-blurred objects.
• Towards Real-Time Automatic Portrait Matting on Mobile Devices
  8 Apr 2019 2 repositories listed
  We tackle the problem of automatic portrait matting on mobile devices.
• Semantic Human Matting
  5 Sep 2018 2 repositories listed
  SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks.
• Real-time deep hair matting on mobile devices
  19 Dec 2017 2 repositories listed
  Augmented reality is an emerging technology in many application domains.
• MaSS13K: A Matting-level Semantic Segmentation Benchmark
  24 Mar 2025 1 repository listed
  MaSS13K features precise masks, with an average mask complexity 20-50 times higher than existing semantic segmentation datasets.
• VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
  11 Mar 2025 1 repository listed
  We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption.
• BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
  8 Jan 2025 1 repository listed
  As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation.
• Memory Efficient Matting with Adaptive Token Routing
  14 Dec 2024 1 repository listed
  Specifically, the router employs a local-global strategy to predict the routing probability of each token, and the LTRM utilizes efficient modules to simulate global attention.
• ZIM: Zero-Shot Image Matting for Anything
  1 Nov 2024 1 repository listed
  To address this limitation, we propose a novel zero-shot image matting model, called ZIM, with two key contributions: First, we develop a label converter that transforms segmentation labels into detailed matte labels,…
• DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios
  13 Oct 2024 1 repository listed
  (2) Existing works are limited to a single type of user input, which is ineffective for intention understanding and also inefficient for user operation.
• Towards Natural Image Matting in the Wild via Real-Scenario Prior
  9 Oct 2024 1 repository listed
  For training objectives, the proposed regularization and trimap loss aim to retain the prior from the pre-trained model and push the matting logits extracted from the mask decoder to contain trimap-based semantic…

Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.