PaintSeg: Training-free Segmentation via Painting
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which creates a contrast between the original image and a painted image in which a masked area is painted using off-the-shelf generative models. During the painting process, inpainting and outpainting are alternated, with the former masking the foreground and filling in the background, and the latter masking the background while recovering the missing part of the foreground object. Inpainting and outpainting, also referred to as I-step and O-step, allow our method to gradually advance the target segmentation mask toward the ground truth without supervision or training. PaintSeg can be configured to work with a variety of prompts, e.g. coarse masks, boxes, scribbles, and points. Our experimental results demonstrate that PaintSeg outperforms existing approaches in coarse mask-prompt, box-prompt, and point-prompt segmentation tasks, providing a training-free solution suitable for unsupervised segmentation.
Code (1)
Tasks
Referring Image Matting (Prompt-based)SegmentationZero Shot SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PaintSeg: Painting Pixels for Training-free Segmentation
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which creates a contrast between the original im…
Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models
Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object. Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal mask…
DiversitySegmentationGenerative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
This paper presents a new adversarial training framework for image inpainting with segmentation confusion adversarial training (SCAT) and contrastive learning. SCAT plays an adversarial game between an inpainting generat…
Contrastive LearningImage InpaintingInpainting Transformer for Anomaly Detection
Anomaly detection in computer vision is the task of identifying images which deviate from a set of normal images. A common approach is to train deep convolutional autoencoders to inpaint covered parts of an image and com…
Anomaly DetectionBi-Directional MS Lesion Filling and Synthesis Using Denoising Diffusion Implicit Model-based Lesion Repainting
Automatic magnetic resonance (MR) image processing pipelines are widely used to study people with multiple sclerosis (PwMS), encompassing tasks such as lesion segmentation and brain parcellation. However, the presence of…
DenoisingImage InpaintingLesion SegmentationSegmentation