Image Matting
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 8
- 보존된 평가 기록
- 45
Image Matting is the process of accurately estimating the foreground object in images and videos. It is a very important technique in image and video editing applications, particularly in film production for creating visual effects. In case of image segmentation, we segment the image into foreground and background by labeling the pixels. Image segmentation generates a binary image, in which a pixel either belongs to foreground or background. However, Image Matting is different from the image segmentation, wherein some pixels may belong to foreground as well as background, such pixels are called partial or mixed pixels. In order to fully separate the foreground from the background in an image, accurate estimation of the alpha values for partial or mixed pixels is necessary.
Source: Automatic Trimap Generation for Image Matting
Image Source: Real-Time High-Resolution Background Matting
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Lightweight high-resolution Subject Matting in the Real World
Diffusion for Natural Image Matting
DiffusionMat: Alpha Matting as Sequential Refinement Learning
Lightweight Portrait Matting via Regional Attention and Refinement
Video Instance Matting
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting
On Point Affiliation in Feature Upsampling
Training-Free Neural Matte Extraction for Visual Effects
Matting Anything
Matte Anything: Interactive Natural Image Matting with Segment Anything Models
Color-aware Deep Temporal Backdrop Duplex Matting System
dugMatting: Decomposed-Uncertainty-Guided Matting
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
Adversarially-Guided Portrait Matting
Adaptive Human Matting for Dynamic Videos
Deep Image Matting: A Comprehensive Survey
Disentangled Pre-training for Image Matting
Revisiting Context Aggregation for Image Matting
CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
TransMatting: Tri-token Equipped Transformer Model for Image Matting
Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting
Privileged Prior Information Distillation for Image Matting
FactorMatte: Redefining Video Matting for Re-Composition Tasks
Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning
Hierarchical and Progressive Image Matting
Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
Robust Human Matting via Semantic Guidance
SAPA: Similarity-Aware Point Affiliation for Feature Upsampling
3D Matting: A Soft Segmentation Method Applied in Computed Tomography
SGM-Net: Semantic Guided Matting Net
Self-supervised Matting-specific Portrait Enhancement and Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.