Wonwoong Cho

Wonwoong Cho, Ziyu Gong, 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.

Wonwoong Cho, Hareesh Ravi, Midhun Harikumar et al.

As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally incorporate the disentangled conditions during the sampling process have been underexplored. In this paper, we present a training framework for feature disentanglement of Diffusion Models (FDiff). We further propose two sampling methods that can boost the realism of our Diffusion Models and also enhance the controllability. Concisely, we train Diffusion Models conditioned on two latent features, a spatial content mask, and a flattened style embedding. We rely on the inductive bias of the denoising process of Diffusion Models to encode pose/layout information in the content feature and semantic/style information in the style feature. Regarding the sampling methods, we first generalize Composable Diffusion Models (GCDM) by breaking the conditional independence assumption to allow for some dependence between conditional inputs, which is shown to be effective in realistic generation in our experiments. Second, we propose timestep-dependent weight scheduling for content and style features to further improve the performance. We also observe better controllability of our proposed methods compared to existing methods in image manipulation and image translation.

Wonwoong Cho, Sungha Choi, David Keetae Park et al.

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. Finally, our code is available at https://github.com/WonwoongCho/GDWCT.

Wonwoong Cho, Yanxia Zhang, Yan-Ying Chen et al.

Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, cross-modal conceptual blending for humans is prone to cognitive biases, like design fixation, which leads to local minima in the design space. In this paper, we propose a T2I diffusion adapter "IT-Blender" that can automate the blending process to enhance human creativity. Prior works related to cross-modal conceptual blending are limited in encoding a real image without loss of details or in disentangling the image and text inputs. To address these gaps, IT-Blender leverages pretrained diffusion models (SD and FLUX) to blend the latent representations of a clean reference image with those of the noisy generated image. Combined with our novel blended attention, IT-Blender encodes the real reference image without loss of details and blends the visual concept with the object specified by the text in a disentangled way. Our experiment results show that IT-Blender outperforms the baselines by a large margin in blending visual and textual concepts, shedding light on the new application of image generative models to augment human creativity.

Wonwoong Cho, Yan-Ying Chen, Matthew Klenk et al.

Text-to-Image (T2I) Diffusion Models have achieved remarkable performance in generating high quality images. However, enabling precise control of continuous attributes, especially multiple attributes simultaneously, in a new domain (e.g., numeric values like eye openness or car width) with text-only guidance remains a significant challenge. To address this, we introduce the Attribute (Att) Adapter, a novel plug-and-play module designed to enable fine-grained, multi-attributes control in pretrained diffusion models. Our approach learns a single control adapter from a set of sample images that can be unpaired and contain multiple visual attributes. The Att-Adapter leverages the decoupled cross attention module to naturally harmonize the multiple domain attributes with text conditioning. We further introduce Conditional Variational Autoencoder (CVAE) to the Att-Adapter to mitigate overfitting, matching the diverse nature of the visual world. Evaluations on two public datasets show that Att-Adapter outperforms all LoRA-based baselines in controlling continuous attributes. Additionally, our method enables a broader control range and also improves disentanglement across multiple attributes, surpassing StyleGAN-based techniques. Notably, Att-Adapter is flexible, requiring no paired synthetic data for training, and is easily scalable to multiple attributes within a single model.

Myunggi Lee, Wonwoong Cho, Moonheum Kim et al.

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.

Wonwoong Cho, Inyeop Lee, David Inouye

While facial attribute manipulation of 2D images via Generative Adversarial Networks (GANs) has become common in computer vision and graphics due to its many practical uses, research on 3D attribute manipulation is relatively undeveloped. Existing 3D attribute manipulation methods are limited because the same semantic changes are applied to every 3D face. The key challenge for developing better 3D attribute control methods is the lack of paired training data in which one attribute is changed while other attributes are held fixed -- e.g., a pair of 3D faces where one is male and the other is female but all other attributes, such as race and expression, are the same. To overcome this challenge, we design a novel pipeline for generating paired 3D faces by harnessing the power of GANs. On top of this pipeline, we then propose an enhanced non-linear 3D conditional attribute controller that increases the precision and diversity of 3D attribute control compared to existing methods. We demonstrate the validity of our dataset creation pipeline and the superior performance of our conditional attribute controller via quantitative and qualitative evaluations.

Wonwoong Cho, Kangyeol Kim, Eungyeup Kim et al.

Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an input image containing its own content is an important issue, but existing methods followed relatively simple approaches, leaving room for improvement especially when incorporating significant style changes. In response, we propose an advanced normalization technique based on adaptive convolution (AdaCoN), in order to properly impose style information into the content of an input image. In detail, after locally standardizing the content representation in a channel-wise manner, AdaCoN performs adaptive convolution where the convolution filter weights are dynamically estimated using the encoded style representation. The flexibility of AdaCoN can handle complicated image translation tasks involving significant style changes. Our qualitative and quantitative experiments demonstrate the superiority of our proposed method against various existing approaches that inject the style into the content.

Wonwoong Cho, Seunghwan Choi, Junwoo Park et al.

Recently, image-to-image translation has obtained significant attention. Among many, those approaches based on an exemplar image that contains the target style information has been actively studied, due to its capability to handle multimodality as well as its applicability in practical use. However, two intrinsic problems exist in the existing methods: what and where to transfer. First, those methods extract style from an entire exemplar which includes noisy information, which impedes a translation model from properly extracting the intended style of the exemplar. That is, we need to carefully determine what to transfer from the exemplar. Second, the extracted style is applied to the entire input image, which causes unnecessary distortion in irrelevant image regions. In response, we need to decide where to transfer the extracted style. In this paper, we propose a novel approach that extracts out a local mask from the exemplar that determines what style to transfer, and another local mask from the input image that determines where to transfer the extracted style. The main novelty of this paper lies in (1) the highway adaptive instance normalization technique and (2) an end-to-end translation framework which achieves an outstanding performance in reflecting a style of an exemplar. We demonstrate the quantitative and qualitative evaluation results to confirm the advantages of our proposed approach.

Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho et al.

This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. In contrast to existing approaches, our model can understand rich text, whether it is a single word, a phrase, or a sentence, and generate multiple possible palettes from it. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT). Our proposed model called Text2Colors consists of two conditional generative adversarial networks: the text-to-palette generation networks and the palette-based colorization networks. The former captures the semantics of the text input and produce relevant color palettes. The latter colorizes a grayscale image using the generated color palette. Our evaluation results show that people preferred our generated palettes over ground truth palettes and that our model can effectively reflect the given palette when colorizing an image.