Image Matting

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
Oct 26, 2026Shuyun Wang, Shangchen Zhou, Peiqing Yang +3Image Matting
The University of Queensland · S-Lab, Nanyang Technological University · University of Adelaide
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Oct 22, 2026Tianming Liang, Junyi Pan, Yuxi Li +5Image Matting Fine-Grained Visual Perception
WeChat Vision, Tencent Inc.
RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image Matting
Aug 9, 2026Zecheng Ren, Yafei Hu, Jianing Zhao +3Diffusion Model Alignment Image Segmentation
Waseda University · Shanghai Jiao Tong University · National University of Singapore
Parallax Portrait Matting
Jul 13, 2026Xin Cai, Jiawen Chen, Lars Jebe +2Image Segmentation Image Editing
Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China · Shanghai AI Laboratory, Shanghai, China · Adobe NextCam, San Jose, CA, USA +1
Self-supervised Automatic Matting
Jul 11, 2026Xiaonan Hu, Zhiyuan Lu, Jingdong Zhao +1Image Segmentation Image Matting
Huazhong University of Science and Technology, China · Beijing Normal University, China · Waseda University, Japan
SAM2Matting: Generalized Image and Video Matting
Jun 25, 2026Ruiqi Shen, Guangquan Jie, Chang Liu +1Image Matting Fine-Grained Visual Perception
Fudan University · Shanghai University of Finance and Economics
αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
May 29, 2026Xiang Zhang, Yang Zhang, Lukas Mehl +3Depth Estimation Stereo Vision
1ETH Zürich · 2DisneyResearch|Studios
CineMatte: Background Matting for Virtual Production and Beyond
May 18, 2026Yuanjian He, Chen Zhang, Fasheng Chen +1Image Editing Image Matting
Online Video Business Unit, Tencent PCG
LiWi: Layering in the Wild
May 14, 2026Yu He, Fang Li, Haoyang Tong +7Intrinsic Image Decomposition Synthetic Data Generation
MAIS & NLPR, CASIA

Oct 26, 2026J/K move · Enter open · S save

MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting

Shuyun Wang, Shangchen Zhou, Peiqing Yang, Yuekun Dai+2

The University of Queensland · S-Lab, Nanyang Technological University · University of Adelaide

Image Matting

Open paper AskPDF arXiv

High-resolution video matting requires preserving fine details, such as hair strands and soft transparency, while maintaining consistency across frames. Memory-based methods achieve strong matting quality by matching current-frame features with information stored from earlier frames, but this process becomes increasingly costly as resolution grows. We present MatAnyone-E, an efficient extension of MatAnyone 2 that focuses computation where it is most needed. Our approach first performs low-resolution propagation to identify uncertain regions that require closer inspection and the memory candidates most relevant to them. It then performs high-resolution matching only for these regions using the selected memory, while reusing low-resolution matching results elsewhere. This strategy reduces both the number of locations requiring detailed matching and the amount of memory searched, while preserving the information needed to produce a complete matte. We further reduce the cost of generating high-resolution mattes with a lightweight decoder designed around measured runtime bottlenecks and trained to reproduce the original decoder's representations. Experiments show that MatAnyone-E maintains matting quality comparable to MatAnyone 2 while achieving an estimated 7.4x inference speedup and reducing peak GPU memory usage to 7.6% of the usage of MatAnyone 2 at 4K. With compilation-enabled inference on a single NVIDIA H200 GPU, it reaches 73.07 FPS at 1080p and 28.62 FPS at 4K.