Taewon Kang

Taewon Kang, Divya Kothandaraman, Dinesh Manocha et al.

Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and intricate scenes. Conversely, 3D-free methods can generate text-controlled views of complex, in-the-wild scenes using a pretrained stable diffusion model without the need for a large amount of 3D-based training data, but lack camera control. In this paper, we introduce a method capable of generating camera-controlled viewpoints from a single input image, by combining the benefits of 3D-free and 3D-based approaches. Our method excels in handling complex and diverse scenes without extensive training or additional 3D and multiview data. It leverages widely available pretrained NVS models for weak guidance, integrating this knowledge into a 3D-free view synthesis style approach, along with enriching the CLIP vision-language space with 3D camera angle information, to achieve the desired results. Experimental results demonstrate that our method outperforms existing models in both qualitative and quantitative evaluations, achieving high-fidelity, consistent novel view synthesis at desired camera angles across a wide variety of scenes while maintaining accurate, natural detail representation and image clarity across various viewpoints. We also support our method with a comprehensive analysis of 2D image generation models and the 3D space, providing a solid foundation and rationale for our solution.

Taewon Kang, Kwang Hee Lee

Unsupervised image translation aims to learn the transformation from a source domain to another target domain given unpaired training data. Several state-of-the-art works have yielded impressive results in the GANs-based unsupervised image-to-image translation. It fails to capture strong geometric or structural changes between domains, or it produces unsatisfactory result for complex scenes, compared to local texture mapping tasks such as style transfer. Recently, SAGAN (Han Zhang, 2018) showed that the self-attention network produces better results than the convolution-based GAN. However, the effectiveness of the self-attention network in unsupervised image-to-image translation tasks have not been verified. In this paper, we propose an unsupervised image-to-image translation with self-attention networks, in which long range dependency helps to not only capture strong geometric change but also generate details using cues from all feature locations. In experiments, we qualitatively and quantitatively show superiority of the proposed method compared to existing state-of-the-art unsupervised image-to-image translation task. The source code and our results are online: https://github.com/itsss/img2img_sa and http://itsc.kr/2019/01/24/2019_img2img_sa

Taewon Kang, Matthias Zwicker

Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented in training data, such as a snowy beach or a rainbow at night, the generation process frequently collapses toward more common alternatives. We identify this failure mode as default completion bias, where denoising trajectories are implicitly attracted toward high-frequency semantic configurations. Existing guidance mechanisms do not explicitly model this competing tendency and therefore struggle to prevent such collapse. We introduce Default Completion Repulsion (DCR), a training-free framework that explicitly models and suppresses default completion behavior. DCR constructs a counterfactual attractor by relaxing the rare compositional factor while preserving surrounding semantics, inducing an alternative denoising trajectory reflecting the model's preferred completion. We define the discrepancy between target and attractor trajectories as a counterfactual drift, and propose a projection-based repulsion mechanism that removes guidance components aligned with this drift direction. This suppresses undesired frequent completions while preserving other semantic components. DCR operates entirely within the standard diffusion sampling process without retraining or architectural modification. Experiments on rare compositional prompts show that DCR improves compositional fidelity while maintaining visual quality. Our analysis further shows that the framework exposes and counteracts intrinsic model biases, offering a new perspective on controllable generation beyond explicit constraint enforcement.

Taewon Kang, Joseph K J, Chris Tensmeyer et al.

We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a \emph{latent masking} formulation that softly attenuates updates in the diffusion space, inspired by smooth barrier functions in physics and numerical optimization. In addition, we introduce \emph{Automated Readability Optimization (ARO)}, which automatically places semi-transparent, rounded backing shapes behind text regions. ARO determines the minimal opacity needed to satisfy perceptual contrast standards (WCAG 2.2) relative to the underlying background, ensuring readability while maintaining aesthetic harmony without human intervention. Multi-page consistency is maintained through a summarization-and-instruction process, where each page is distilled into a compact representation that recursively guides subsequent generations. This design reflects how humans build continuity by retaining prior context, ensuring that visual motifs evolve coherently across an entire document. Our method further treats a document as a structured composition in which text, figures, and backgrounds are preserved or regenerated as separate layers, allowing targeted background editing without compromising readability. Finally, user-provided prompts allow stylistic adjustments in color and texture, balancing automated consistency with flexible customization. Our training-free framework produces visually coherent, text-preserving, and thematically aligned documents, bridging generative modeling with natural design workflows.

Taewon Kang, Divya Kothandaraman, Ming C. Lin

Generating coherent long-form video sequences from discrete input using only text prompts is a critical task in content creation. While diffusion-based models excel at short video synthesis, long-form storytelling from text remains largely unexplored and a challenge due to difficulties in temporal coherency, preserving semantic meaning, and maintaining both scene context and action continuity across the video. We introduce a novel storytelling framework that achieves this by integrating scene and action prompts through dynamics-inspired prompt mixing. Specifically, we first present a bidirectional time-weighted latent blending strategy to ensure temporal consistency between segments of the long-form video being generated. We then propose a dynamics-informed prompt weighting (DIPW) mechanism that adaptively balances the influence of scene and action prompts at each diffusion timestep by jointly considering CLIP-based alignment, narrative continuity, and temporal smoothness. To further enhance motion continuity, we incorporate a semantic action representation to encode high-level action semantics into the blending process, dynamically adjusting transitions based on action similarity and ensuring smooth yet adaptable motion changes. Latent space blending maintains spatial coherence between objects in a scene, while time-weighted blending enforces bidirectional constraints for temporal consistency. The resulting integrative system prevents abrupt transitions while ensuring fluid storytelling that faithfully reflects both scene and action cues. Extensive experiments demonstrate significant improvements over baselines, achieving temporally consistent and visually compelling video narratives without any additional training. This approach bridges the gap between short clips and extended video to establish a new paradigm in GenAI-driven video synthesis from text.

Taewon Kang, Ming C. Lin

Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic negation in diffusion-based generative models by modeling it as a structured feasibility constraint on semantic guidance within diffusion dynamics. Rather than introducing heuristics or retraining model parameters, we reinterpret classifier-free guidance as defining a semantic update direction and enforce negation by projecting the update onto a convex constraint set derived from linguistic structure. This novel formulation provides a unified framework for handling diverse negation phenomena, including object absence, graded non-inversion semantics, multi-negation composition, and scope-sensitive disambiguation. Our approach is training-free, compatible with pretrained diffusion backbones, and naturally extends from image generation to temporally evolving video trajectories. In addition, we introduce a structured negation-centric benchmark suite that isolates distinct linguistic failure modes in generative systems, to further research in this area. Experiments demonstrate that our method achieves robust negation compliance while preserving visual fidelity and structural coherence, establishing the first unified formulation of linguistic negation in diffusion-based generative models beyond representation-level evaluation.

Taewon Kang

We present a diffusion-based framework for document-centric background generation that achieves foreground preservation and multi-page stylistic consistency through latent-space design rather than explicit constraints. Instead of suppressing diffusion updates or applying masking heuristics, our approach reinterprets diffusion as the evolution of stochastic trajectories through a structured latent space. By shaping the initial noise and its geometric alignment, background generation naturally avoids designated foreground regions, allowing readable content to remain intact without auxiliary mechanisms. To address the long-standing issue of stylistic drift across pages, we decouple style control from text conditioning and introduce cached style directions as persistent vectors in latent space. Once selected, these directions constrain diffusion trajectories to a shared stylistic subspace, ensuring consistent appearance across pages and editing iterations. This formulation eliminates the need for repeated prompt-based style specification and provides a more stable foundation for multi-page generation. Our framework admits a geometric and physical interpretation, where diffusion paths evolve on a latent manifold shaped by preferred directions, and foreground regions are rarely traversed as a consequence of trajectory initialization rather than explicit exclusion. The proposed method is training-free, compatible with existing diffusion backbones, and produces visually coherent, foreground-preserving results across complex documents. By reframing diffusion as trajectory design in latent space, we offer a principled approach to consistent and structured generative modeling.

Xiyi Chen, Shaofei Wang, Marko Mihajlovic et al.

We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh, the aligned SMPL-X body mesh, and a Gaussian-splat representation for photorealistic novel-view rendering. Prior methods for clothed human reconstruction either optimize parametric templates, which overlook loose garments and human-object interactions, or train implicit functions under simplified camera assumptions, limiting applicability in real scenes. In contrast, HART predicts per-pixel 3D point maps, normals, and body correspondences, and employs an occlusion-aware Poisson reconstruction to recover complete geometry, even in self-occluded regions. These predictions also align with a parametric SMPL-X body model, ensuring that reconstructed geometry remains consistent with human structure while capturing loose clothing and interactions. These human-aligned meshes initialize Gaussian splats to further enable sparse-view rendering. While trained on only 2.3K synthetic scans, HART achieves state-of-the-art results: Chamfer Distance improves by 18-23 percent for clothed-mesh reconstruction, PA-V2V drops by 6-27 percent for SMPL-X estimation, LPIPS decreases by 15-27 percent for novel-view synthesis on a wide range of datasets. These results suggest that feed-forward transformers can serve as a scalable model for robust human reconstruction in real-world settings. Code and models will be released.

Taewon Kang, Ming C. Lin

Recent advances in scene-based video generation have enabled systems to synthesize coherent visual narratives from structured prompts. However, a crucial dimension of storytelling -- character-driven dialogue and speech -- remains underexplored. In this paper, we present a modular pipeline that transforms action-level prompts into visually and auditorily grounded narrative dialogue, enriching visual storytelling with natural voice and character expression. Our method takes as input a pair of prompts per scene, where the first defines the setting and the second specifies a character's behavior. While a story generation model such as Text2Story produces the corresponding visual scene, we focus on generating expressive, character-consistent utterances grounded in both the prompts and the scene image. A pretrained vision-language encoder extracts high-level semantic features from a representative frame, capturing salient visual context. These features are then integrated with structured prompts to guide a large language model in synthesizing natural dialogue. To ensure contextual and emotional consistency across scenes, we introduce a Recursive Narrative Bank -- a speaker-aware, temporally structured memory that recursively accumulates each character's dialogue history. Inspired by Script Theory in cognitive psychology, this design enables characters to speak in ways that reflect their evolving goals, social context, and narrative roles throughout the story. Finally, we render each utterance as expressive, character-conditioned speech, resulting in fully-voiced, multimodal video narratives. Our training-free framework generalizes across diverse story settings -- from fantasy adventures to slice-of-life episodes -- offering a scalable solution for coherent, character-grounded audiovisual storytelling.

Taewon Kang, Sunghyun Park, Seunghwan Choi et al.

Image-based virtual try-on provides the capacity to transfer a clothing item onto a photo of a given person, which is usually accomplished by warping the item to a given human pose and adjusting the warped item to the person. However, the results of real-world synthetic images (e.g., selfies) from the previous method is not realistic because of the limitations which result in the neck being misrepresented and significant changes to the style of the garment. To address these challenges, we propose a novel method to solve this unique issue, called VITON-CROP. VITON-CROP synthesizes images more robustly when integrated with random crop augmentation compared to the existing state-of-the-art virtual try-on models. In the experiments, we demonstrate that VITON-CROP is superior to VITON-HD both qualitatively and quantitatively.

Taewon Kang, Younghoon Shin

We propose an indoor navigation algorithm based on pedestrian dead reckoning (PDR) using an inertial measurement unit in a smartphone and map matching. The proposed indoor navigation system is user-friendly and convenient because it requires no additional device except a smartphone and works with a pedestrian in a casual posture who is walking with a smartphone in their hand. Because the performance of the PDR decreases over time, we greatly reduced the position error of the trajectory estimated by PDR using a map matching method with a known indoor map. To verify the proposed indoor navigation algorithm, we conducted an experiment in a real indoor environment using a commercial Android smartphone. The performance of our algorithm was demonstrated through the results of the experiment.

Bumju Kwak, Jiwon Park, Taewon Kang et al.

In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information of molecular structures, resulting in less intuitive representations. Moreover, the widely used message-passing mechanism is limited to provide the interpretation of experimental results from a chemical perspective. To address these challenges, we introduce a novel Transformer-based framework for molecular representation learning, named the Geometry-aware Transformer (GeoT). GeoT learns molecular graph structures through attention-based mechanisms specifically designed to offer reliable interpretability, as well as molecular property prediction. Consequently, GeoT can generate attention maps of interatomic relationships associated with training objectives. In addition, GeoT demonstrates comparable performance to MPNN-based models while achieving reduced computational complexity. Our comprehensive experiments, including an empirical simulation, reveal that GeoT effectively learns the chemical insights into molecular structures, bridging the gap between artificial intelligence and molecular sciences.

Taewon Kang

Existing state-of-the-art techniques in exemplar-based image-to-image translation hold several critical concerns. Existing methods related to exemplar-based image-to-image translation are impossible to translate on an image tuple input (source, target) that is not aligned. Additionally, we can confirm that the existing method exhibits limited generalization ability to unseen images. In order to overcome this limitation, we propose Multiple GAN Inversion for Exemplar-based Image-to-Image Translation. Our novel Multiple GAN Inversion avoids human intervention by using a self-deciding algorithm to choose the number of layers using Fréchet Inception Distance(FID), which selects more plausible image reconstruction results among multiple hypotheses without any training or supervision. Experimental results have in fact, shown the advantage of the proposed method compared to existing state-of-the-art exemplar-based image-to-image translation methods.

Taewon Kang, Soohyun Kim, Sunwoo Kim et al.

Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters on domain-specific and task-specific benchmarks, thus having limited applicability and generalization ability. In this paper, we propose a novel framework, for the first time, to solve exemplar-based translation through an online optimization given an input image pair, called online exemplar fine-tuning (OEFT), in which we fine-tune the off-the-shelf and general-purpose networks to the input image pair themselves. We design two sub-networks, namely correspondence fine-tuning and multiple GAN inversion, and optimize these network parameters and latent codes, starting from the pre-trained ones, with well-defined loss functions. Our framework does not require the off-line training phase, which has been the main challenge of existing methods, but the pre-trained networks to enable optimization in online. Experimental results prove that our framework is effective in having a generalization power to unseen image pairs and clearly even outperforms the state-of-the-arts needing the intensive training phase.