Supplementary Material: Deep Image Harmonization

نویسندگان

  • Yi-Hsuan Tsai
  • Xiaohui Shen
  • Zhe Lin
  • Kalyan Sunkavalli
  • Xin Lu
  • Ming-Hsuan Yang
چکیده

To validate the effectiveness of our joint training scheme, we also try an alternative of incorporating an off-the-shelf state-of-the-art scene parsing model [3] into our single encoder-decoder harmonization framework to provide semantic information. This network architecture is shown in Figure 1. We show quantitative comparisons on our synthesized dataset in Table 1 and 2. The MSE and PSNR of the results generated from the framework with the separate scene parsing model is worse than our joint model, where the scene parsing decoder is learned from scratch as described in the main manuscript. It shows that our joint training scheme can achieve better harmonization results than the one based on separate training.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Supplementary Material: Deep Adaptive Image Clustering

This is the supplementary material for the paper entitled “Deep Adaptive Image Clustering”. The supplementary material is organized as follows. Section 1 gives the mapping function described in Figure 1. Section 2 presents the proof of Theorem 1. Section 3 details the experimental settings in our experiments. 1. The Mapping Function Utilized in Figure 1 We assume that li represents the label fe...

متن کامل

Characteristics of Smoothing Filters to Achieve the Guideline Recommended Positron Emission Tomography Image without Harmonization

Objective(s): The aim of this study is to examine the effect of different smoothing filters on the image quality and SUVmax to achieve the guideline recommended positron emission tomography (PET) image without harmonization. Methods: We used a Biograph mCT PET scanner. A National Electrical Manufacturers Association (NEMA) the International Electrotechnical Commission (IEC) body phantom was fil...

متن کامل

Aggregating Image and Text Quantized Correlated Components Supplementary Material

This is the supplementary material to the article Aggregating Image and Text Quantized Correlated Components published at CVPR 2016. While not necessary to understand the work exposed in the paper, it reports some complementary results or “interesting negative results”. Last section focuses on providing implementation details to reproduce the experiments, in particular regarding the material co...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017