DeepAI AI Chat
Log In Sign Up

DeePaste – Inpainting for Pasting

by   Levi Kassel Michael Werman, et al.
Hebrew University of Jerusalem

One of the challenges of supervised learning training is the need to procure an substantial amount of tagged data. A well-known method of solving this problem is to use synthetic data in a copy-paste fashion, so that we cut objects and paste them onto relevant backgrounds. Pasting the objects naively results in artifacts that cause models to give poor results on real data. We present a new method for cleanly pasting objects on different backgrounds so that the dataset created gives competitive performance on real data. The main emphasis is on the treatment of the border of the pasted object using inpainting. We show state-of-the-art results both on instance detection and foreground segmentation


page 2

page 3

page 5


Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection

A major impediment in rapidly deploying object detection models for inst...

MOVE: Unsupervised Movable Object Segmentation and Detection

We introduce MOVE, a novel method to segment objects without any form of...

Foreground-aware Image Inpainting

Existing image inpainting methods typically fill holes by borrowing info...

Perceptual Artifacts Localization for Inpainting

Image inpainting is an essential task for multiple practical application...

BYEL : Bootstrap on Your Emotion Latent

According to the problem of dataset construction cost for training in de...

Semantic Foreground Inpainting from Weak Supervision

Semantic scene understanding is an essential task for self-driving vehic...

Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

The goal of this work is to efficiently identify visually similar patter...