Jaeseok Jeong

Jaeseok Jeong, Mingi Kwon, Youngjung Uh

Diffusion models (DMs) synthesize high-quality images in various domains. However, controlling their generative process is still hazy because the intermediate variables in the process are not rigorously studied. Recently, the bottleneck feature of the U-Net, namely $h$-space, is found to convey the semantics of the resulting image. It enables StyleCLIP-like latent editing within DMs. In this paper, we explore further usage of $h$-space beyond attribute editing, and introduce a method to inject the content of one image into another image by combining their features in the generative processes. Briefly, given the original generative process of the other image, 1) we gradually blend the bottleneck feature of the content with proper normalization, and 2) we calibrate the skip connections to match the injected content. Unlike custom-diffusion approaches, our method does not require time-consuming optimization or fine-tuning. Instead, our method manipulates intermediate features within a feed-forward generative process. Furthermore, our method does not require supervision from external networks. The code is available at https://curryjung.github.io/InjectFusion/

Taewoo Kim, Jaeseok Jeong, Hoonhee Cho et al.

In low-light conditions, capturing videos with frame-based cameras often requires long exposure times, resulting in motion blur and reduced visibility. While frame-based motion deblurring and low-light enhancement have been studied, they still pose significant challenges. Event cameras have emerged as a promising solution for improving image quality in low-light environments and addressing motion blur. They provide two key advantages: capturing scene details well even in low light due to their high dynamic range, and effectively capturing motion information during long exposures due to their high temporal resolution. Despite efforts to tackle low-light enhancement and motion deblurring using event cameras separately, previous work has not addressed both simultaneously. To explore the joint task, we first establish real-world datasets for event-guided low-light enhancement and deblurring using a hybrid camera system based on beam splitters. Subsequently, we introduce an end-to-end framework to effectively handle these tasks. Our framework incorporates a module to efficiently leverage temporal information from events and frames. Furthermore, we propose a module to utilize cross-modal feature information to employ a low-pass filter for noise suppression while enhancing the main structural information. Our proposed method significantly outperforms existing approaches in addressing the joint task. Our project pages are available at https://github.com/intelpro/ELEDNet.

Mingi Kwon, Jaeseok Jeong, Youngjung Uh

Diffusion models achieve outstanding generative performance in various domains. Despite their great success, they lack semantic latent space which is essential for controlling the generative process. To address the problem, we propose asymmetric reverse process (Asyrp) which discovers the semantic latent space in frozen pretrained diffusion models. Our semantic latent space, named h-space, has nice properties for accommodating semantic image manipulation: homogeneity, linearity, robustness, and consistency across timesteps. In addition, we introduce a principled design of the generative process for versatile editing and quality boost ing by quantifiable measures: editing strength of an interval and quality deficiency at a timestep. Our method is applicable to various architectures (DDPM++, iD- DPM, and ADM) and datasets (CelebA-HQ, AFHQ-dog, LSUN-church, LSUN- bedroom, and METFACES). Project page: https://kwonminki.github.io/Asyrp/

Daehee Park, Jaeseok Jeong, Sung-Hoon Yoon et al.

Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from unreliable predictions under distribution shifts during test time. Accordingly, several online learning methods have been proposed using regression loss from the ground truth of observed data leveraging the auto-labeling nature of trajectory prediction task. We mainly tackle the following two issues. First, previous works underfit and overfit as they only optimize the last layer of the motion decoder. To this end, we employ the masked autoencoder (MAE) for representation learning to encourage complex interaction modeling in shifted test distribution for updating deeper layers. Second, utilizing the sequential nature of driving data, we propose an actor-specific token memory that enables the test-time learning of actor-wise motion characteristics. Our proposed method has been validated across various challenging cross-dataset distribution shift scenarios including nuScenes, Lyft, Waymo, and Interaction. Our method surpasses the performance of existing state-of-the-art online learning methods in terms of both prediction accuracy and computational efficiency. The code is available at https://github.com/daeheepark/T4P.

Jibin Song, Mingi Kwon, Jaeseok Jeong et al.

In this work, we show that the impact of model capacity varies across timesteps: it is crucial for the early and late stages but largely negligible during the intermediate stage. Accordingly, we propose FlowBlending, a stage-aware multi-model sampling strategy that employs a large model and a small model at capacity-sensitive stages and intermediate stages, respectively. We further introduce simple criteria to choose stage boundaries and provide a velocity-divergence analysis as an effective proxy for identifying capacity-sensitive regions. Across LTX-Video (2B/13B) and WAN 2.1 (1.3B/14B), FlowBlending achieves up to 1.65x faster inference with 57.35% fewer FLOPs, while maintaining the visual fidelity, temporal coherence, and semantic alignment of the large models. FlowBlending is also compatible with existing sampling-acceleration techniques, enabling up to 2x additional speedup. Project page is available at: https://jibin86.github.io/flowblending_project_page.

Jaeseok Jeong, Junho Kim, Gayoung Lee et al.

In the domain of text-to-image generation, diffusion models have emerged as powerful tools. Recently, studies on visual prompting, where images are used as prompts, have enabled more precise control over style and content. However, existing methods often suffer from content leakage, where undesired elements of the visual style prompt are transferred along with the intended style. To address this issue, we 1) extend classifier-free guidance (CFG) to utilize swapping self-attention and propose 2) negative visual query guidance (NVQG) to reduce the transfer of unwanted contents. NVQG employs negative score by intentionally simulating content leakage scenarios that swap queries instead of key and values of self-attention layers from visual style prompts. This simple yet effective method significantly reduces content leakage. Furthermore, we provide careful solutions for using a real image as visual style prompts. Through extensive evaluation across various styles and text prompts, our method demonstrates superiority over existing approaches, reflecting the style of the references, and ensuring that resulting images match the text prompts. Our code is available \href{https://github.com/naver-ai/StyleKeeper}{here}.

Jaeseok Jeong, Junho Kim, Yunjey Choi et al.

In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage. To address these challenges, we propose a novel approach, \ours, to produce a diverse range of images while maintaining specific style elements and nuances. During the denoising process, we keep the query from original features while swapping the key and value with those from reference features in the late self-attention layers. This approach allows for the visual style prompting without any fine-tuning, ensuring that generated images maintain a faithful style. Through extensive evaluation across various styles and text prompts, our method demonstrates superiority over existing approaches, best reflecting the style of the references and ensuring that resulting images match the text prompts most accurately. Our project page is available https://curryjung.github.io/VisualStylePrompt/.

Kim Shin Seong, Mingi Kwon, Jaeseok Jeong et al.

Rectified flow is a generative model that learns smooth transport mappings between two distributions through an ordinary differential equation (ODE). Unlike diffusion-based generative models, which require costly numerical integration of a generative ODE to sample images with state-of-the-art quality, rectified flow uses an iterative process called reflow to learn smooth and straight ODE paths. This allows for relatively simple and efficient generation of high-quality images. However, rectified flow still faces several challenges. 1) The reflow process requires a large number of generative pairs to preserve the target distribution, leading to significant computational costs. 2) Since the model is typically trained using only generated image pairs, its performance heavily depends on the 1-rectified flow model, causing it to become biased towards the generated data. In this work, we experimentally expose the limitations of the original rectified flow and propose a novel approach that incorporates real images into the training process. By preserving the ODE paths for real images, our method effectively reduces reliance on large amounts of generated data. Instead, we demonstrate that the reflow process can be conducted efficiently using a much smaller set of generated and real images. In CIFAR-10, we achieved significantly better FID scores, not only in one-step generation but also in full-step simulations, while using only of the generative pairs compared to the original method. Furthermore, our approach induces straighter paths and avoids saturation on generated images during reflow, leading to more robust ODE learning while preserving the distribution of real images.

Jibin Song, Mingi Kwon, Jaeseok Jeong et al.

Text-to-video and image-to-video generation have made rapid progress in visual quality, but they remain limited in controlling the precise timing of motion. In contrast, audio provides temporal cues aligned with video motion, making it a promising condition for temporally controlled video generation. However, existing audio-to-video (A2V) models struggle with fine-grained synchronization due to indirect conditioning mechanisms or limited temporal modeling capacity. We present Syncphony, which generates 380x640 resolution, 24fps videos synchronized with diverse audio inputs. Our approach builds upon a pre-trained video backbone and incorporates two key components to improve synchronization: (1) Motion-aware Loss, which emphasizes learning at high-motion regions; (2) Audio Sync Guidance, which guides the full model using a visually aligned off-sync model without audio layers to better exploit audio cues at inference while maintaining visual quality. To evaluate synchronization, we propose CycleSync, a video-to-audio-based metric that measures the amount of motion cues in the generated video to reconstruct the original audio. Experiments on AVSync15 and The Greatest Hits datasets demonstrate that Syncphony outperforms existing methods in both synchronization accuracy and visual quality. Project page is available at: https://jibin86.github.io/syncphony_project_page

Jongoh Jeong, Hunmin Yang, Jaeseok Jeong et al.

Transfer attacks optimize on a surrogate and deploy to a black-box target. While iterative optimization attacks in this paradigm are limited by their per-input cost limits efficiency and scalability due to multistep gradient updates for each input, generative attacks alleviate these by producing adversarial examples in a single forward pass at test time. However, current generative attacks still adhere to optimizing surrogate losses (e.g., feature divergence) and overlook the generator's internal dynamics, underexploring how the generator's internal representations shape transferable perturbations. To address this, we enforce semantic consistency by aligning the early generator's intermediate features to an EMA teacher, stabilizing object-aligned representations and improving black-box transfer without inference-time overhead. To ground the mechanism, we quantify semantic stability as the standard deviation of foreground IoU between cluster-derived activation masks and foreground masks across generator blocks, and observe reduced semantic drift under our method. For more reliable evaluation, we also introduce Accidental Correction Rate (ACR) to separate inadvertent corrections from intended misclassifications, complementing the inherent blind spots in traditional Attack Success Rate (ASR), Fooling Rate (FR), and Accuracy metrics. Across architectures, domains, and tasks, our approach can be seamlessly integrated into existing generative attacks with consistent improvements in black-box transfer, while maintaining test-time efficiency.

Sung-Hoon Yoon, Hyeokjun Kweon, Jaeseok Jeong et al.

Existing studies in weakly supervised semantic segmentation (WSSS) have utilized class activation maps (CAMs) to localize the class objects. However, since a classification loss is insufficient for providing precise object regions, CAMs tend to be biased towards discriminative patterns (i.e., sparseness) and do not provide precise object boundary information (i.e., impreciseness). To resolve these limitations, we propose a novel framework (composed of MainNet and SupportNet.) that derives pixel-level self-supervision from given image-level supervision. In our framework, with the help of the proposed Regional Contrastive Module (RCM) and Multi-scale Attentive Module (MAM), MainNet is trained by self-supervision from the SupportNet. The RCM extracts two forms of self-supervision from SupportNet: (1) class region masks generated from the CAMs and (2) class-wise prototypes obtained from the features according to the class region masks. Then, every pixel-wise feature of the MainNet is trained by the prototype in a contrastive manner, sharpening the resulting CAMs. The MAM utilizes CAMs inferred at multiple scales from the SupportNet as self-supervision to guide the MainNet. Based on the dissimilarity between the multi-scale CAMs from MainNet and SupportNet, CAMs from the MainNet are trained to expand to the less-discriminative regions. The proposed method shows state-of-the-art WSSS performance both on the train and validation sets on the PASCAL VOC 2012 dataset. For reproducibility, code will be available publicly soon.

Yeonkun Lee, Jaeseok Jeong, Jongseob Yun et al.

Omni-directional cameras have many advantages overconventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have beenproposed recently to apply convolutional neural networks(CNNs) to omni-directional images for various visual tasks.However, most of them use image representations defined inthe Euclidean space after transforming the omni-directionalviews originally formed in the non-Euclidean space. Thistransformation leads to shape distortion due to nonuniformspatial resolving power and the loss of continuity. Theseeffects make existing convolution kernels experience diffi-culties in extracting meaningful information.This paper presents a novel method to resolve such prob-lems of applying CNNs to omni-directional images. Theproposed method utilizes a spherical polyhedron to rep-resent omni-directional views. This method minimizes thevariance of the spatial resolving power on the sphere sur-face, and includes new convolution and pooling methodsfor the proposed representation. The proposed method canalso be adopted by any existing CNN-based methods. Thefeasibility of the proposed method is demonstrated throughclassification, detection, and semantic segmentation taskswith synthetic and real datasets.