paper-with-me

Image Matting

8개 벤치마크 · 논문 234편 · 이 태스크의 논문 보기 →

Benchmarks

Composition-1K

결과 13개

AM-2K

결과 9개

P3M-10k

결과 7개

AIM-500

결과 6개

Adobe Matting

결과 4개

Distinctions-646

결과 4개

AMD

결과 1개

PPM-100

결과 1개

Most implemented

Deep Image Matting

2017-03-10 · 구현 8개

Index Network

2019-08-11 · 구현 6개

Papers

Self-supervised Automatic Matting

2026-07-11 · Xiaonan Hu, Zhiyuan Lu, Jingdong Zhao, Hao Lu arxiv

High-quality alpha mattes are notoriously expensive to annotate, creating a fundamental data bottleneck for deep image matting. While prior work attempts to reduce annotation cost using coarser labels like trimaps or mas…

Image Matting

SAM2Matting: Generalized Image and Video Matting

2026-06-25 · Ruiqi Shen, Guangquan Jie, Chang Liu, Henghui Ding arxiv

Despite impressive advances in image matting, video matting remains challenging due to the inherent gap between high-level tracking, which requires frame-wise understanding, and low-level matting, which focuses on extrem…

Domain GeneralizationImage Matting

Toward Real-World High-Precision Image Matting and Segmentation

2026-01-17 · Haipeng Zhou, Zhaohu Xing, Hongqiu Wang, Jun Ma 외 arxiv

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foregro…

Domain AdaptationScene ParsingImage Matting

Segment and Matte Anything in a Unified Model

2026-01-17 · Zezhong Fan, Xiaohan Li, Topojoy Biswas, Kaushiki Nag 외 arxiv

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accur…

Zero-shot GeneralizationImage SegmentationImage Matting

Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views

2026-01-06 · Xiang Zhang, Yang Zhang, Lukas Mehl, Markus Gross 외 arxiv

Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foreground and background cues. This paper intro…

Monocular Depth EstimationNovel View SynthesisImage Matting

MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

2025-12-12 · Peiqing Yang, Shangchen Zhou, Kai Hao, Qingyi Tao arxiv

Video matting remains limited by the scale and realism of existing datasets. While leveraging segmentation data can enhance semantic stability, the lack of effective boundary supervision often leads to segmentation-like …

Image Matting

전체 234편 보기 →