Wonwoong Cho

Wonwoong Cho

Auto-generated profile, based on publicly available information

Wonwoong Cho

Purdue University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2019
Verified
Conference Paper
Closed access
WCWonwoong Cho
Wonwoong Cho
SCSungha Choi
Sungha Choi
DPDavid Keetae Park
David Keetae Park
ISInkyu Shin
Inkyu Shin
JCJaegul Choo
Jaegul Choo
Recently, unsupervised exemplar-based image-to-image translation, conditioned on a given exemplar without the paired data, has accomplished substantial advancements. In order to transfer the information from an exemplar to an input image, existing methods often use a normalization technique, e.g., adaptive instance normalization, that controls the channel-wise statistics of an input activation map at a particular layer, such as the mean and the variance. Meanwhile, style transfer approaches similar task to image translation by nature, demonstrated superior performance by using the higher-order statistics such as covariance among channels in representing a style. In detail, it works via whitening (given a zero-mean input feature, transforming its covariance matrix into the identity). followed by coloring (changing the covariance matrix of the whitened feature to those of the style feature). However, applying this approach in image translation is computationally intensive and error-prone due to the expensive time complexity and its non-trivial backpropagation. In response, this paper proposes an end-to-end approach tailored for image translation that efficiently approximates this transformation with our novel regularization methods. We further extend our approach to a group-wise form for memory and time efficiency as well as image quality. Extensive qualitative and quantitative experiments demonstrate that our proposed method is fast, both in training and inference, and highly effective in reflecting the style of an exemplar.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
HBHyojin Bahng
Hyojin Bahng
SYSeungjoo Yoo
Seungjoo Yoo
WCWonwoong Cho
Wonwoong Cho
DPDavid Keetae Park
David Keetae Park
ZWZiming Wu
Ziming Wu
JCJaeyul Choo
Jaeyul Choo

2 December 2024
Verified
Book Chapter
Closed access
PDF file
WCWonwoong Cho
Wonwoong Cho
HRHareesh Ravi
Hareesh Ravi
MHMidhun Harikumar
Midhun Harikumar
VKVinh Khuc
Vinh Khuc
KSKrishna Kumar Singh
Krishna Kumar Singh
AKAjinkya Kale
Ajinkya Kale

1 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
WCWonwoong Cho
Wonwoong Cho
ZGZiyu Gong
Ziyu Gong
DIDavid I. Inouye
David I. Inouye
Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate. A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple distributions. Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD). Importantly, our problem reduces to a min-min, i.e., cooperative, problem and can provide a natural evaluation metric for unsupervised distribution alignment. We show empirical results on both simulated and real-world datasets to demonstrate the benefits of our approach. Code is available at https://github.com/inouye-lab/alignment-upper-bound.

25 November 2020 in arXiv
Verified
Preprint
Open access
PDF file
MLMyunggi Lee
Myunggi Lee
WCWonwoong Cho
Wonwoong Cho
MKMoonheum Kim
Moonheum Kim
DIDavid Inouye
David Inouye
NKNojun Kwak
Nojun Kwak
Reconstructing 3D human faces in the wild with the 3D Morphable Model (3DMM) has become popular in recent years. While most prior work focuses on estimating more robust and accurate geometry, relatively little attention has been paid to improving the quality of the texture model. Meanwhile, with the advent of Generative Adversarial Networks (GANs), there has been great progress in reconstructing realistic 2D images. Recent work demonstrates that GANs trained with abundant high-quality UV maps can produce high-fidelity textures superior to those produced by existing methods. However, acquiring such high-quality UV maps is difficult because they are expensive to acquire, requiring laborious processes to refine. In this work, we present a novel UV map generative model that learns to generate diverse and realistic synthetic UV maps without requiring high-quality UV maps for training. Our proposed framework can be trained solely with in-the-wild images (i.e., UV maps are not required) by leveraging a combination of GANs and a differentiable renderer. Both quantitative and qualitative evaluations demonstrate that our proposed texture model produces more diverse and higher fidelity textures compared to existing methods.