DeepAI AI Chat
Log In Sign Up

Semantic Foreground Inpainting from Weak Supervision

by   Chenyang Lu, et al.
TU Eindhoven

Semantic scene understanding is an essential task for self-driving vehicles and mobile robots. In our work, we aim to estimate a semantic segmentation map, in which the foreground objects are removed and semantically inpainted with background classes, from a single RGB image. This semantic foreground inpainting task is performed by a single-stage convolutional neural network (CNN) that contains our novel max-pooling as inpainting (MPI) module, which is trained with weak supervision, i.e., it does not require manual background annotations for the foreground regions to be inpainted. Our approach is inherently more efficient than the previous two-stage state-of-the-art method, and outperforms it by a margin of 3 on Cityscapes. The performance margin increases to 6 unseen KITTI dataset. The code and the manually annotated datasets for testing are shared with the research community at


page 1

page 2

page 4

page 5

page 6

page 7


Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network

Foreground segmentation in video sequences is a classic topic in compute...

Foreground-aware Image Inpainting

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

Semantic Image Matting

Natural image matting separates the foreground from background in fracti...

Automatic Semantic Content Removal by Learning to Neglect

We introduce a new system for automatic image content removal and inpain...

Volumetric Disentanglement for 3D Scene Manipulation

Recently, advances in differential volumetric rendering enabled signific...

DeePaste – Inpainting for Pasting

One of the challenges of supervised learning training is the need to pro...