Junyong Noh

Chang Wook Seo, Amirsaman Ashtari, Junyong Noh

Sketches reflect the drawing style of individual artists; therefore, it is important to consider their unique styles when extracting sketches from color images for various applications. Unfortunately, most existing sketch extraction methods are designed to extract sketches of a single style. Although there have been some attempts to generate various style sketches, the methods generally suffer from two limitations: low quality results and difficulty in training the model due to the requirement of a paired dataset. In this paper, we propose a novel multi-modal sketch extraction method that can imitate the style of a given reference sketch with unpaired data training in a semi-supervised manner. Our method outperforms state-of-the-art sketch extraction methods and unpaired image translation methods in both quantitative and qualitative evaluations.

Soojin Choi, Seokhyeon Hong, Chaelin Kim et al.

Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body proportions. In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, the proposed method dynamically repositions anchors to reachable regions on the target character. This is achieved via a Transformer-based anchor refinement strategy that predicts anchor displacements and constrains the translated anchors to remain on the target character geometry through differentiable soft projection. By incorporating pose-dependent spatial structures from the source character, the adapted anchors provide structurally coherent guidance for interaction-aware retargeting. Conditioned on these anchors, a graph-based autoencoder predicts target skeletal motion that preserves the spatial configuration of the source. To encourage task-aligned optimization between anchor adaptation and motion retargeting, we adopt an alternating training scheme in which each module is optimized in turn. Through extensive evaluations, we demonstrate that our method outperforms state-of-the-art approaches in preserving interaction fidelity across diverse character geometries.

Seokhyeon Hong, Chaelin Kim, Serin Yoon et al.

Text-driven motion generation has advanced significantly with the rise of denoising diffusion models. However, previous methods often oversimplify representations for the skeletal joints, temporal frames, and textual words, limiting their ability to fully capture the information within each modality and their interactions. Moreover, when using pre-trained models for downstream tasks, such as editing, they typically require additional efforts, including manual interventions, optimization, or fine-tuning. In this paper, we introduce a skeleton-aware latent diffusion (SALAD), a model that explicitly captures the intricate inter-relationships between joints, frames, and words. Furthermore, by leveraging cross-attention maps produced during the generation process, we enable attention-based zero-shot text-driven motion editing using a pre-trained SALAD model, requiring no additional user input beyond text prompts. Our approach significantly outperforms previous methods in terms of text-motion alignment without compromising generation quality, and demonstrates practical versatility by providing diverse editing capabilities beyond generation. Code is available at project page.

Junhyuk Jeon, Seokhyeon Hong, Junyong Noh

Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to as style. Recent approaches have tackled this challenge by attaching a style injection mechanism to a pretrained text-driven diffusion model. Existing stylization methods, however, either require style-specific fine-tuning of existing models or rely on heavy ControlNet-based architectures, limiting efficiency and generalization to unseen styles. We propose a lightweight style conditioning framework that dynamically modulates a pretrained diffusion model through hypernetwork-generated LoRA parameters. A style reference motion is encoded into a global style embedding, which is mapped by a hypernetwork to low-rank updates applied at each denoising step of the diffusion model. By structuring the style latent space with a supervised contrastive loss, our framework reliably captures diverse stylistic attributes, improves generalization to unseen styles, and supports optimization-based guidance without requiring predefined style categories. Experiments on the HumanML3D and 100STYLE datasets show state-of-the-art stylization results, while achieving improved stylization for unseen styles.

Kwan Yun, Chaelin Kim, Hangyeul Shin et al.

Recent 3D face editing methods using masks have produced high-quality edited images by leveraging Neural Radiance Fields (NeRF). Despite their impressive performance, existing methods often provide limited user control due to the use of pre-trained segmentation masks. To utilize masks with a desired layout, an extensive training dataset is required, which is challenging to gather. We present FFaceNeRF, a NeRF-based face editing technique that can overcome the challenge of limited user control due to the use of fixed mask layouts. Our method employs a geometry adapter with feature injection, allowing for effective manipulation of geometry attributes. Additionally, we adopt latent mixing for tri-plane augmentation, which enables training with a few samples. This facilitates rapid model adaptation to desired mask layouts, crucial for applications in fields like personalized medical imaging or creative face editing. Our comparative evaluations demonstrate that FFaceNeRF surpasses existing mask based face editing methods in terms of flexibility, control, and generated image quality, paving the way for future advancements in customized and high-fidelity 3D face editing. The code is available on the {\href{https://kwanyun.github.io/FFaceNeRF_page/}{project-page}}.

Yeonsoo Choi, Inyup Lee, Sihun Cha et al.

In the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated 3D characters that deviate significantly from human facial structures. In this scenario, it is important to consider the target character's facial structure and possible range of motion to preserve the semantics assumed by the original facial motions after the retargeting. To achieve this, we propose a local patch-based retargeting method that transfers facial animations captured in a source performance video to a target stylized 3D character. Our method consists of three modules. The Automatic Patch Extraction Module extracts local patches from the source video frame. These patches are processed through the Reenactment Module to generate correspondingly re-enacted target local patches. The Weight Estimation Module calculates the animation parameters for the target character at every frame for the creation of a complete facial animation sequence. Extensive experiments demonstrate that our method can successfully transfer the semantic meaning of source facial expressions to stylized characters with considerable variations in facial feature proportion.

Minsun Kim, Dawon Lee, Junyong Noh

On general video-sharing platforms like YouTube, comments are displayed independently of video playback. As viewers often read comments while watching a video, they may encounter ones referring to moments unrelated to the current scene, which can reveal spoilers and disrupt immersion. To address this problem, we present ComVi, a novel system that displays comments at contextually relevant moments, enabling viewers to see time-synchronized comments and video content together. We first map all comments to relevant video timestamps by computing audio-visual correlation, then construct the comment sequence through an optimization that considers temporal relevance, popularity (number of likes), and display duration for comfortable reading. In a user study, ComVi provided a significantly more engaging experience than conventional video interfaces (i.e., YouTube and Danmaku), with 71.9% of participants selecting ComVi as their most preferred interface.

Kwan Yun, Kwanggyoon Seo, Chang Wook Seo et al.

Facial sketches are both a concise way of showing the identity of a person and a means to express artistic intention. While a few techniques have recently emerged that allow sketches to be extracted in different styles, they typically rely on a large amount of data that is difficult to obtain. Here, we propose StyleSketch, a method for extracting high-resolution stylized sketches from a face image. Using the rich semantics of the deep features from a pretrained StyleGAN, we are able to train a sketch generator with 16 pairs of face and the corresponding sketch images. The sketch generator utilizes part-based losses with two-stage learning for fast convergence during training for high-quality sketch extraction. Through a set of comparisons, we show that StyleSketch outperforms existing state-of-the-art sketch extraction methods and few-shot image adaptation methods for the task of extracting high-resolution abstract face sketches. We further demonstrate the versatility of StyleSketch by extending its use to other domains and explore the possibility of semantic editing. The project page can be found in https://kwanyun.github.io/stylesketch_project.

Kwan Yun, Changmin Lee, Ayeong Jeong et al.

Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models are publicly available at https://kwanyun.github.io/StyleID_page/

Kwan Yun, Youngseo Kim, Kwanggyoon Seo et al.

We introduce DiffSketch, a method for generating a variety of stylized sketches from images. Our approach focuses on selecting representative features from the rich semantics of deep features within a pretrained diffusion model. This novel sketch generation method can be trained with one manual drawing. Furthermore, efficient sketch extraction is ensured by distilling a trained generator into a streamlined extractor. We select denoising diffusion features through analysis and integrate these selected features with VAE features to produce sketches. Additionally, we propose a sampling scheme for training models using a conditional generative approach. Through a series of comparisons, we verify that distilled DiffSketch not only outperforms existing state-of-the-art sketch extraction methods but also surpasses diffusion-based stylization methods in the task of extracting sketches.

Jongwoo Choi, Kwanggyoon Seo, Amirsaman Ashtari et al.

We propose a method that can generate cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN. Inspired by the success of recent unconditional video generation, we leverage a powerful pre-trained image generator to synthesize high-quality cinemagraphs. Unlike previous approaches that mainly utilize the latent space of a pre-trained StyleGAN, our approach utilizes its deep feature space for both GAN inversion and cinemagraph generation. Specifically, we propose multi-scale deep feature warping (MSDFW), which warps the intermediate features of a pre-trained StyleGAN at different resolutions. By using MSDFW, the generated cinemagraphs are of high resolution and exhibit plausible looping animation. We demonstrate the superiority of our method through user studies and quantitative comparisons with state-of-the-art cinemagraph generation methods and a video generation method that uses a pre-trained StyleGAN.

Kwan Yun, Seokhyeon Hong, Chaelin Kim et al.

Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets. In this work, we introduce AnyMoLe, a novel method that addresses this limitation by leveraging video diffusion models to generate motion in-between frames for arbitrary characters without external data. Our approach employs a two-stage frame generation process to enhance contextual understanding. Furthermore, to bridge the domain gap between real-world and rendered character animations, we introduce ICAdapt, a fine-tuning technique for video diffusion models. Additionally, we propose a ``motion-video mimicking'' optimization technique, enabling seamless motion generation for characters with arbitrary joint structures using 2D and 3D-aware features. AnyMoLe significantly reduces data dependency while generating smooth and realistic transitions, making it applicable to a wide range of motion in-betweening tasks.

Soyeon Yoon, Kwan Yun, Kwanggyoon Seo et al.

Recent advances in 3D face stylization have made significant strides in few to zero-shot settings. However, the degree of stylization achieved by existing methods is often not sufficient for practical applications because they are mostly based on statistical 3D Morphable Models (3DMM) with limited variations. To this end, we propose a method that can produce a highly stylized 3D face model with desired topology. Our methods train a surface deformation network with 3DMM and translate its domain to the target style using a paired exemplar. The network achieves stylization of the 3D face mesh by mimicking the style of the target using a differentiable renderer and directional CLIP losses. Additionally, during the inference process, we utilize a Mesh Agnostic Encoder (MAGE) that takes deformation target, a mesh of diverse topologies as input to the stylization process and encodes its shape into our latent space. The resulting stylized face model can be animated by commonly used 3DMM blend shapes. A set of quantitative and qualitative evaluations demonstrate that our method can produce highly stylized face meshes according to a given style and output them in a desired topology. We also demonstrate example applications of our method including image-based stylized avatar generation, linear interpolation of geometric styles, and facial animation of stylized avatars.

Seungmi Lee, Kwan Yun, Junyong Noh

We introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user-defined text descriptions specifying a target style. Building upon a pre-trained mesh deformation network and a texture generator for original 3DMM-based realistic human faces, our approach fine-tunes these models using stylized facial images generated via text-guided image-to-image (i2i) translation with a diffusion model, which serve as stylization targets for the rendered mesh. To prevent undesired changes in identity, facial alignment, or expressions during i2i translation, we introduce a stylization method that explicitly preserves the facial attributes of the source image. By maintaining these critical attributes during image stylization, the proposed approach ensures consistent 3D style transfer across the 3DMM parameter space through image-based training. Once trained, StyleMM enables feed-forward generation of stylized face meshes with explicit control over shape, expression, and texture parameters, producing meshes with consistent vertex connectivity and animatability. Quantitative and qualitative evaluations demonstrate that our approach outperforms state-of-the-art methods in terms of identity-level facial diversity and stylization capability. The code and videos are available at [kwanyun.github.io/stylemm_page](kwanyun.github.io/stylemm_page).

Sihun Cha, Serin Yoon, Kwanggyoon Seo et al.

Accurately retargeting facial expressions to a face mesh while enabling manipulation is a key challenge in facial animation retargeting. Recent deep-learning methods address this by encoding facial expressions into a global latent code, but they often fail to capture fine-grained details in local regions. While some methods improve local accuracy by transferring deformations locally, this often complicates overall control of the facial expression. To address this, we propose a method that combines the strengths of both global and local deformation models. Our approach enables intuitive control and detailed expression cloning across diverse face meshes, regardless of their underlying structures. The core idea is to localize the influence of the global latent code on the target mesh. Our model learns to predict skinning weights for each vertex of the target face mesh through indirect supervision from predefined segmentation labels. These predicted weights localize the global latent code, enabling precise and region-specific deformations even for meshes with unseen shapes. We supervise the latent code using Facial Action Coding System (FACS)-based blendshapes to ensure interpretability and allow straightforward editing of the generated animation. Through extensive experiments, we demonstrate improved performance over state-of-the-art methods in terms of expression fidelity, deformation transfer accuracy, and adaptability across diverse mesh structures.

Seokhyeon Hong, Soojin Choi, Chaelin Kim et al.

Despite the growing accessibility of skeletal motion data, integrating it for animating character meshes remains challenging due to diverse configurations of both skeletons and meshes. Specifically, the body scale and bone lengths of the skeleton should be adjusted in accordance with the size and proportions of the mesh, ensuring that all joints are accurately positioned within the character mesh. Furthermore, defining skinning weights is complicated by variations in skeletal configurations, such as the number of joints and their hierarchy, as well as differences in mesh configurations, including their connectivity and shapes. While existing approaches have made efforts to automate this process, they hardly address the variations in both skeletal and mesh configurations. In this paper, we present a novel method for the automatic rigging and skinning of character meshes using skeletal motion data, accommodating arbitrary configurations of both meshes and skeletons. The proposed method predicts the optimal skeleton aligned with the size and proportion of the mesh as well as defines skinning weights for various mesh-skeleton configurations, without requiring explicit supervision tailored to each of them. By incorporating Diffusion 3D Features (Diff3F) as semantic descriptors of character meshes, our method achieves robust generalization across different configurations. To assess the performance of our method in comparison to existing approaches, we conducted comprehensive evaluations encompassing both quantitative and qualitative analyses, specifically examining the predicted skeletons, skinning weights, and deformation quality.

Gihoon Kim, Kwanggyoon Seo, Sihun Cha et al.

Audio-driven talking head generation is advancing from 2D to 3D content. Notably, Neural Radiance Field (NeRF) is in the spotlight as a means to synthesize high-quality 3D talking head outputs. Unfortunately, this NeRF-based approach typically requires a large number of paired audio-visual data for each identity, thereby limiting the scalability of the method. Although there have been attempts to generate audio-driven 3D talking head animations with a single image, the results are often unsatisfactory due to insufficient information on obscured regions in the image. In this paper, we mainly focus on addressing the overlooked aspect of 3D consistency in the one-shot, audio-driven domain, where facial animations are synthesized primarily in front-facing perspectives. We propose a novel method, NeRFFaceSpeech, which enables to produce high-quality 3D-aware talking head. Using prior knowledge of generative models combined with NeRF, our method can craft a 3D-consistent facial feature space corresponding to a single image. Our spatial synchronization method employs audio-correlated vertex dynamics of a parametric face model to transform static image features into dynamic visuals through ray deformation, ensuring realistic 3D facial motion. Moreover, we introduce LipaintNet that can replenish the lacking information in the inner-mouth area, which can not be obtained from a given single image. The network is trained in a self-supervised manner by utilizing the generative capabilities without additional data. The comprehensive experiments demonstrate the superiority of our method in generating audio-driven talking heads from a single image with enhanced 3D consistency compared to previous approaches. In addition, we introduce a quantitative way of measuring the robustness of a model against pose changes for the first time, which has been possible only qualitatively.

Sihun Cha, Kwanggyoon Seo, Amirsaman Ashtari et al.

There has been significant progress in generating an animatable 3D human avatar from a single image. However, recovering texture for the 3D human avatar from a single image has been relatively less addressed. Because the generated 3D human avatar reveals the occluded texture of the given image as it moves, it is critical to synthesize the occluded texture pattern that is unseen from the source image. To generate a plausible texture map for 3D human avatars, the occluded texture pattern needs to be synthesized with respect to the visible texture from the given image. Moreover, the generated texture should align with the surface of the target 3D mesh. In this paper, we propose a texture synthesis method for a 3D human avatar that incorporates geometry information. The proposed method consists of two convolutional networks for the sampling and refining process. The sampler network fills in the occluded regions of the source image and aligns the texture with the surface of the target 3D mesh using the geometry information. The sampled texture is further refined and adjusted by the refiner network. To maintain the clear details in the given image, both sampled and refined texture is blended to produce the final texture map. To effectively guide the sampler network to achieve its goal, we designed a curriculum learning scheme that starts from a simple sampling task and gradually progresses to the task where the alignment needs to be considered. We conducted experiments to show that our method outperforms previous methods qualitatively and quantitatively.

Sanghun Park, Kwanggyoon Seo, Junyong Noh

We propose Neural Crossbreed, a feed-forward neural network that can learn a semantic change of input images in a latent space to create the morphing effect. Because the network learns a semantic change, a sequence of meaningful intermediate images can be generated without requiring the user to specify explicit correspondences. In addition, the semantic change learning makes it possible to perform the morphing between the images that contain objects with significantly different poses or camera views. Furthermore, just as in conventional morphing techniques, our morphing network can handle shape and appearance transitions separately by disentangling the content and the style transfer for rich usability. We prepare a training dataset for morphing using a pre-trained BigGAN, which generates an intermediate image by interpolating two latent vectors at an intended morphing value. This is the first attempt to address image morphing using a pre-trained generative model in order to learn semantic transformation. The experiments show that Neural Crossbreed produces high quality morphed images, overcoming various limitations associated with conventional approaches. In addition, Neural Crossbreed can be further extended for diverse applications such as multi-image morphing, appearance transfer, and video frame interpolation.