Log In Sign Up

Multi-scale Self-calibrated Network for Image Light Source Transfer

by   Yuanzhi Wang, et al.

Image light source transfer (LLST), as the most challenging task in the domain of image relighting, has attracted extensive attention in recent years. In the latest research, LLST is decomposed three sub-tasks: scene reconversion, shadow estimation, and image re-rendering, which provides a new paradigm for image relighting. However, many problems for scene reconversion and shadow estimation tasks, including uncalibrated feature information and poor semantic information, are still unresolved, thereby resulting in insufficient feature representation. In this paper, we propose novel down-sampling feature self-calibrated block (DFSB) and up-sampling feature self-calibrated block (UFSB) as the basic blocks of feature encoder and decoder to calibrate feature representation iteratively because the LLST is similar to the recalibration of image light source. In addition, we fuse the multi-scale features of the decoder in scene reconversion task to further explore and exploit more semantic information, thereby providing more accurate primary scene structure for image re-rendering. Experimental results in the VIDIT dataset show that the proposed approach significantly improves the performance for LLST.


page 2

page 6

page 7


Inharmonious Region Localization

The advance of image editing techniques allows users to create artistic ...

Deep Relighting Networks for Image Light Source Manipulation

Manipulating the light source of given images is an interesting task and...

Self-attention on Multi-Shifted Windows for Scene Segmentation

Scene segmentation in images is a fundamental yet challenging problem in...

Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition

Semantic information has been proved effective in scene text recognition...

EGFN: Efficient Geometry Feature Network for Fast Stereo 3D Object Detection

Fast stereo based 3D object detectors have made great progress in the se...

Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition

Although text recognition has significantly evolved over the years, stat...

Code Repositories


An official implementation of "Multi-scale Self-calibrated Network for Image Light Source Transfer" (CVPRW 2021) in PyTorch.

view repo