Sunghyun Cho

Dongwoo Lee, Jeongtaek Oh, Jaesung Rim et al.

We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6-DOF camera trajectory-based motion blur formulation and voxel-based radiance fields. From extremely blurred images, we optimize the sharp radiance fields by jointly estimating the camera trajectories that generate the blurry images. In training, multiple rays along the camera trajectory are accumulated to reconstruct single blurry color, which is equivalent to the physical motion blur operation. We minimize the photo-consistency loss on blurred image space and obtain the sharp radiance fields with camera trajectories that explain the blur of all images. The joint optimization on the blurred image space demands painfully increasing computation and resources proportional to the blur size. Our method solves this problem by replacing the MLP-based framework to low-dimensional 6-DOF camera poses and voxel-based radiance fields. Compared with the existing works, our approach restores much sharper 3D scenes from challenging motion blurred views with the order of 10 times less training time and GPU memory consumption.

Sohyun Lee, Jaesung Rim, Boseung Jeong et al.

We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality significantly. To address the first issue, we develop a dedicated camera system and build a new dataset of real low-light images with accurate pose labels. Thanks to our camera system, each low-light image in our dataset is coupled with an aligned well-lit image, which enables accurate pose labeling and is used as privileged information during training. We also propose a new model and a new training strategy that fully exploit the privileged information to learn representation insensitive to lighting conditions. Our method demonstrates outstanding performance on real extremely low light images, and extensive analyses validate that both of our model and dataset contribute to the success.

Minsu Gong, Nuri Ryu, Jungseul Ok et al.

Recent advances in image editing leverage latent diffusion models (LDMs) for versatile, text-prompt-driven edits across diverse tasks. Yet, maintaining pixel-level edge structures-crucial for tasks such as photorealistic style transfer or image tone adjustment-remains as a challenge for latent-diffusion-based editing. To overcome this limitation, we propose a novel Structure Preservation Loss (SPL) that leverages local linear models to quantify structural differences between input and edited images. Our training-free approach integrates SPL directly into the diffusion model's generative process to ensure structural fidelity. This core mechanism is complemented by a post-processing step to mitigate LDM decoding distortions, a masking strategy for precise edit localization, and a color preservation loss to preserve hues in unedited areas. Experiments confirm SPL enhances structural fidelity, delivering state-of-the-art performance in latent-diffusion-based image editing. Our code will be publicly released at https://github.com/gongms00/SPL.

Geonung Kim, Kyoungkook Kang, Seongtae Kim et al.

For realistic and vivid colorization, generative priors have recently been exploited. However, such generative priors often fail for in-the-wild complex images due to their limited representation space. In this paper, we propose BigColor, a novel colorization approach that provides vivid colorization for diverse in-the-wild images with complex structures. While previous generative priors are trained to synthesize both image structures and colors, we learn a generative color prior to focus on color synthesis given the spatial structure of an image. In this way, we reduce the burden of synthesizing image structures from the generative prior and expand its representation space to cover diverse images. To this end, we propose a BigGAN-inspired encoder-generator network that uses a spatial feature map instead of a spatially-flattened BigGAN latent code, resulting in an enlarged representation space. Our method enables robust colorization for diverse inputs in a single forward pass, supports arbitrary input resolutions, and provides multi-modal colorization results. We demonstrate that BigColor significantly outperforms existing methods especially on in-the-wild images with complex structures.

Junyong Lee, Myeonghee Lee, Sunghyun Cho et al.

We propose the first reference-based video super-resolution (RefVSR) approach that utilizes reference videos for high-fidelity results. We focus on RefVSR in a triple-camera setting, where we aim at super-resolving a low-resolution ultra-wide video utilizing wide-angle and telephoto videos. We introduce the first RefVSR network that recurrently aligns and propagates temporal reference features fused with features extracted from low-resolution frames. To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module. For learning and evaluation of our network, we present the first RefVSR dataset consisting of triplets of ultra-wide, wide-angle, and telephoto videos concurrently taken from triple cameras of a smartphone. We also propose a two-stage training strategy fully utilizing video triplets in the proposed dataset for real-world 4x video super-resolution. We extensively evaluate our method, and the result shows the state-of-the-art performance in 4x super-resolution.

Kyungmin Jo, Wonjoon Jin, Jaegul Choo et al.

While recent 3D-aware generative models have shown photo-realistic image synthesis with multi-view consistency, the synthesized image quality degrades depending on the camera pose (e.g., a face with a blurry and noisy boundary at a side viewpoint). Such degradation is mainly caused by the difficulty of learning both pose consistency and photo-realism simultaneously from a dataset with heavily imbalanced poses. In this paper, we propose SideGAN, a novel 3D GAN training method to generate photo-realistic images irrespective of the camera pose, especially for faces of side-view angles. To ease the challenging problem of learning photo-realistic and pose-consistent image synthesis, we split the problem into two subproblems, each of which can be solved more easily. Specifically, we formulate the problem as a combination of two simple discrimination problems, one of which learns to discriminate whether a synthesized image looks real or not, and the other learns to discriminate whether a synthesized image agrees with the camera pose. Based on this, we propose a dual-branched discriminator with two discrimination branches. We also propose a pose-matching loss to learn the pose consistency of 3D GANs. In addition, we present a pose sampling strategy to increase learning opportunities for steep angles in a pose-imbalanced dataset. With extensive validation, we demonstrate that our approach enables 3D GANs to generate high-quality geometries and photo-realistic images irrespective of the camera pose.

Hyeongseok Son, Junyong Lee, Sunghyun Cho et al.

While motion compensation greatly improves video deblurring quality, separately performing motion compensation and video deblurring demands huge computational overhead. This paper proposes a real-time video deblurring framework consisting of a lightweight multi-task unit that supports both video deblurring and motion compensation in an efficient way. The multi-task unit is specifically designed to handle large portions of the two tasks using a single shared network, and consists of a multi-task detail network and simple networks for deblurring and motion compensation. The multi-task unit minimizes the cost of incorporating motion compensation into video deblurring and enables real-time deblurring. Moreover, by stacking multiple multi-task units, our framework provides flexible control between the cost and deblurring quality. We experimentally validate the state-of-the-art deblurring quality of our approach, which runs at a much faster speed compared to previous methods, and show practical real-time performance (30.99dB@30fps measured in the DVD dataset).

Seongtae Kim, Kyoungkook Kang, Geonung Kim et al.

Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A naïve solution here is to train a separate model for each domain using few-shot domain adaptation methods. Unfortunately, this approach mandates linearly-scaled computational resources both in memory and computation time and, more importantly, such separate models cannot exploit the shared knowledge between target domains. In this paper, we propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains. DynaGAN has an adaptation module, which is a hyper-network that dynamically adapts a pretrained GAN model into the multiple target domains. Hence, we can fully exploit the shared knowledge across target domains and avoid the linearly-scaled computational requirements. As it is still computationally challenging to adapt a large-size GAN model, we design our adaptation module light-weight using the rank-1 tensor decomposition. Lastly, we propose a contrastive-adaptation loss suitable for multi-domain few-shot adaptation. We validate the effectiveness of our method through extensive qualitative and quantitative evaluations.

Wonjoon Jin, Nuri Ryu, Geonung Kim et al.

While 3D GANs have recently demonstrated the high-quality synthesis of multi-view consistent images and 3D shapes, they are mainly restricted to photo-realistic human portraits. This paper aims to extend 3D GANs to a different, but meaningful visual form: artistic portrait drawings. However, extending existing 3D GANs to drawings is challenging due to the inevitable geometric ambiguity present in drawings. To tackle this, we present Dr.3D, a novel adaptation approach that adapts an existing 3D GAN to artistic drawings. Dr.3D is equipped with three novel components to handle the geometric ambiguity: a deformation-aware 3D synthesis network, an alternating adaptation of pose estimation and image synthesis, and geometric priors. Experiments show that our approach can successfully adapt 3D GANs to drawings and enable multi-view consistent semantic editing of drawings.

Kyoungkook Kang, Gyujin Sim, Sunghyun Cho

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this potential. Decomposition-based methods often struggle with clean separation, while generation-based methods suffer from difficulty in training data acquisition, reducing quality and scene diversity. In this paper, we propose BFS, a novel generation-based framework for layered image synthesis. Specifically, given a background image and user guidance, BFS synthesizes a foreground layer that incorporates not only a foreground object but also its associated visual effects, such as shadows and reflections, while seamlessly harmonizing with the background to produce a coherent composite. To enable diverse and high-quality foreground layer synthesis while overcoming data scarcity, we leverage the comparatively easy-to-learn knowledge of unlayered image synthesis for the foreground synthesis. To this end, we adopt a dual-branch diffusion framework in which two interconnected branches generate a composite image and a foreground layer, respectively, enabling bidirectional knowledge transfer. Based on this framework, we propose a two-stage training scheme that utilizes a high-quality unlayered composite image dataset to effectively enhance foreground quality. Extensive experiments, including a user study, show that BFS produces high-quality layered images, consistently outperforming prior methods.

Seyoung Ahn, Soohyeong Kim, Yongseok Kwon et al.

In 6G mobile communication systems, various AI-based network functions and applications have been standardized. Federated learning (FL) is adopted as the core learning architecture for 6G systems to avoid privacy leakage from mobile user data. However, in FL, users with non-independent and identically distributed (non-IID) datasets can deteriorate the performance of the global model because the convergence direction of the gradient for each dataset is different, thereby inducing a weight divergence problem. To address this problem, we propose a novel diffusion strategy for machine learning (ML) models (FedDif) to maximize the performance of the global model with non-IID data. FedDif enables the local model to learn different distributions before parameter aggregation by passing the local models through users via device-to-device communication. Furthermore, we theoretically demonstrate that FedDif can circumvent the weight-divergence problem. Based on this theory, we propose a communication-efficient diffusion strategy for ML models that can determine the trade-off between learning performance and communication cost using auction theory. The experimental results show that FedDif improves the top-1 test accuracy by up to 34.89\% and reduces communication costs by 14.6% to a maximum of 63.49%.

Youngchan Kim, Wonjoon Jin, Sunghyun Cho et al.

Modeling the spatial radiance distribution of light rays in a scene has been extensively explored for applications, including view synthesis. Spectrum and polarization, the wave properties of light, are often neglected due to their integration into three RGB spectral bands and their non-perceptibility to human vision. However, these properties are known to encompass substantial material and geometric information about a scene. Here, we propose to model spectro-polarimetric fields, the spatial Stokes-vector distribution of any light ray at an arbitrary wavelength. We present Neural Spectro-polarimetric Fields (NeSpoF), a neural representation that models the physically-valid Stokes vector at given continuous variables of position, direction, and wavelength. NeSpoF manages inherently noisy raw measurements, showcases memory efficiency, and preserves physically vital signals - factors that are crucial for representing the high-dimensional signal of a spectro-polarimetric field. To validate NeSpoF, we introduce the first multi-view hyperspectral-polarimetric image dataset, comprised of both synthetic and real-world scenes. These were captured using our compact hyperspectral-polarimetric imaging system, which has been calibrated for robustness against system imperfections. We demonstrate the capabilities of NeSpoF on diverse scenes.

Jiyun Won, Heemin Yang, Woohyeok Kim et al.

Recent work has explored optimizing image signal processing (ISP) pipelines for various tasks by composing predefined modules and adapting them to task-specific objectives. However, jointly optimizing module sequences and parameters remains challenging. Existing approaches rely on neural architecture search (NAS) or step-wise reinforcement learning (RL), but NAS suffers from a training-inference mismatch, while step-wise RL leads to unstable training and high computational overhead due to stage-wise decision-making. We propose POS-ISP, a sequence-level RL framework that formulates modular ISP optimization as a global sequence prediction problem. Our method predicts the entire module sequence and its parameters in a single forward pass and optimizes the pipeline using a terminal task reward, eliminating the need for intermediate supervision and redundant executions. Experiments across multiple downstream tasks show that POS-ISP improves task performance while reducing computational cost, highlighting sequence-level optimization as a stable and efficient paradigm for task-aware ISP. The project page is available at https://w1jyun.github.io/POS-ISP

Nuri Ryu, Minsu Gong, Geonung Kim et al.

We introduce POP3D, a novel framework that creates a full $360^\circ$-view 3D model from a single image. POP3D resolves two prominent issues that limit the single-view reconstruction. Firstly, POP3D offers substantial generalizability to arbitrary categories, a trait that previous methods struggle to achieve. Secondly, POP3D further improves reconstruction fidelity and naturalness, a crucial aspect that concurrent works fall short of. Our approach marries the strengths of four primary components: (1) a monocular depth and normal predictor that serves to predict crucial geometric cues, (2) a space carving method capable of demarcating the potentially unseen portions of the target object, (3) a generative model pre-trained on a large-scale image dataset that can complete unseen regions of the target, and (4) a neural implicit surface reconstruction method tailored in reconstructing objects using RGB images along with monocular geometric cues. The combination of these components enables POP3D to readily generalize across various in-the-wild images and generate state-of-the-art reconstructions, outperforming similar works by a significant margin. Project page: \url{http://cg.postech.ac.kr/research/POP3D}

Gyujin Sim, Seungjoo Shin, Hosung Jeon et al.

Light field displays (LFDs) require rendering an interlaced image that encodes many view-dependent observations. This multi-view requirement introduces substantial computational overhead, making real-time rendering difficult to achieve. While 3D Gaussian Splatting (3DGS) is efficient for single-view rendering on 2D displays, directly extending it to LFDs is computationally expensive. Moreover, prior accelerations either suffer from GPU inefficiency under spatially incoherent subpixel layouts or rely on computationally heavy multi-plane intermediates. In this paper, we propose CoherentRaster, a 3DGS-based light field rendering framework that performs subpixel-level rasterization. Our method employs Cross-view Coherent Attribute Reuse to eliminate redundant computation across neighboring viewpoints and applies View-coherent Remapping to restore warp-level memory efficiency degraded by the interlaced subpixel layout. Together, CoherentRaster provides an efficient pipeline for real-time, high-quality light field synthesis on consumer-grade hardware.

Jeongeun Park, Janghyeok Han, Geonung Kim et al.

Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support such use cases, it must enable large spatial extrapolation over long sequences. However, most existing methods address only one of these challenges or lack explicit mechanisms for ensuring global spatio-temporal consistency, leading to notable limitations. In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. Our approach follows a coarse-to-fine strategy with a two-stage pipeline. We first construct Global Coarse Guidance (GCG), a low-resolution representation that captures global structure and dominant motion across the video. Unlike naive downsampling, GCG is built via a novel global-local frame swapping mechanism that couples sparse global keyframes with local temporal windows and exchanges information during sampling. This enables GCG to encode both long-term structural consistency and short-term temporal dynamics in a unified representation. Guided by this representation, HL-OutPaint then performs high-resolution outpainting to generate spatially detailed and temporally consistent content. By separating global structure modeling from fine-grained synthesis, our framework achieves stable, coherent generation for large spatial expansion and long video sequences. Extensive experiments show that HL-OutPaint outperforms existing methods in challenging scenarios involving wide spatial extrapolation and long video sequences.

Wonjoon Jin, Jiyun Won, Janghyeok Han et al.

Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in commonly used training datasets. To address this, we introduce DynaVid, a video synthesis framework that leverages synthetic motion data in training, which is represented as optical flow and rendered using computer graphics pipelines. This approach offers two key advantages. First, synthetic motion offers diverse motion patterns and precise control signals that are difficult to obtain from real data. Second, unlike rendered videos with artificial appearances, rendered optical flow encodes only motion and is decoupled from appearance, thereby preventing models from reproducing the unnatural look of synthetic videos. Building on this idea, DynaVid adopts a two-stage generation framework: a motion generator first synthesizes motion, and then a motion-guided video generator produces video frames conditioned on that motion. This decoupled formulation enables the model to learn dynamic motion patterns from synthetic data while preserving visual realism from real-world videos. We validate our framework on two challenging scenarios, vigorous human motion generation and extreme camera motion control, where existing datasets are particularly limited. Extensive experiments demonstrate that DynaVid improves the realism and controllability in dynamic motion generation and camera motion control.

Sunung Mun, Sunghyun Cho, Jungseul Ok

Recent text-to-image (T2I) generators can synthesize realistic images, but still struggle with compositional prompts involving multiple objects, counts, attributes, and relations. We introduce EPIC (Efficient Predicate-Guided Inference-Time Control), a training-free inference-time refinement framework for compositional T2I generation. EPIC casts refinement as predicate-guided search: it parses the original prompt once into a fixed visual program of object variables and typed predicates, covering checkable conditions such as object presence, counts, attributes, and relations. Each generated or edited image is verified against this program using visual evidence extracted from that image. An image is judged to satisfy the prompt only when all predicates are satisfied; otherwise, failed predicates decide the next step, routing local failures to targeted editing and global failures to resampling while the fixed visual program remains unchanged. On GenEval2, EPIC improves prompt-level accuracy from 34.16% for single-pass generation with the base generator to 71.46%. Under the same generator/editor setting and maximum image-model execution budget, EPIC outperforms the strongest prior refinement baseline by 19.23 points while reducing realized cost by 31% in image-model executions, 72% in MLLM calls, and 81% in MLLM tokens per prompt.

Woohyeok Kim, Jaesung Rim, Daeyeon Kim et al.

Burst image restoration aims to reconstruct a high-quality image from burst images, which are typically captured using manually designed exposure settings. Although these exposure settings significantly influence the final restoration performance, the problem of finding optimal exposure settings has been overlooked. In this paper, we present Dynamic Exposure Burst Image Restoration (DEBIR), a novel burst image restoration pipeline that enhances restoration quality by dynamically predicting exposure times tailored to the shooting environment. In our pipeline, Burst Auto-Exposure Network (BAENet) estimates the optimal exposure time for each burst image based on a preview image, as well as motion magnitude and gain. Subsequently, a burst image restoration network reconstructs a high-quality image from burst images captured using these optimal exposure times. For training, we introduce a differentiable burst simulator and a three-stage training strategy. Our experiments demonstrate that our pipeline achieves state-of-the-art restoration quality. Furthermore, we validate the effectiveness of our approach on a real-world camera system, demonstrating its practicality.

Nuri Ryu, Jiyun Won, Jooeun Son et al.

High-quality 3D assets are essential for various applications in computer graphics and 3D vision but remain scarce due to significant acquisition costs. To address this shortage, we introduce Elevate3D, a novel framework that transforms readily accessible low-quality 3D assets into higher quality. At the core of Elevate3D is HFS-SDEdit, a specialized texture enhancement method that significantly improves texture quality while preserving the appearance and geometry while fixing its degradations. Furthermore, Elevate3D operates in a view-by-view manner, alternating between texture and geometry refinement. Unlike previous methods that have largely overlooked geometry refinement, our framework leverages geometric cues from images refined with HFS-SDEdit by employing state-of-the-art monocular geometry predictors. This approach ensures detailed and accurate geometry that aligns seamlessly with the enhanced texture. Elevate3D outperforms recent competitors by achieving state-of-the-art quality in 3D model refinement, effectively addressing the scarcity of high-quality open-source 3D assets.

Woohyeok Kim, Geonu Kim, Junyong Lee et al.

RAW images are rarely shared mainly due to its excessive data size compared to their sRGB counterparts obtained by camera ISPs. Learning the forward and inverse processes of camera ISPs has been recently demonstrated, enabling physically-meaningful RAW-level image processing on input sRGB images. However, existing learning-based ISP methods fail to handle the large variations in the ISP processes with respect to camera parameters such as ISO and exposure time, and have limitations when used for various applications. In this paper, we propose ParamISP, a learning-based method for forward and inverse conversion between sRGB and RAW images, that adopts a novel neural-network module to utilize camera parameters, which is dubbed as ParamNet. Given the camera parameters provided in the EXIF data, ParamNet converts them into a feature vector to control the ISP networks. Extensive experiments demonstrate that ParamISP achieve superior RAW and sRGB reconstruction results compared to previous methods and it can be effectively used for a variety of applications such as deblurring dataset synthesis, raw deblurring, HDR reconstruction, and camera-to-camera transfer.

Wonjoon Jin, Qi Dai, Chong Luo et al.

We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. This approach offers two key benefits. Since optical flow can be directly estimated from videos, our approach allows for the use of arbitrary training videos without ground-truth camera parameters. Moreover, as background optical flow encodes 3D correlation across different viewpoints, our method enables detailed camera control by leveraging the background motion. To synthesize natural object motion while supporting detailed camera control, our framework adopts a two-stage video synthesis pipeline consisting of optical flow generation and flow-conditioned video synthesis. Extensive experiments demonstrate the superiority of our method over previous approaches in terms of accurate camera control and natural object motion synthesis.

Seungjoo Shin, Jaesik Park, Sunghyun Cho

We present LocoGS, a locality-aware 3D Gaussian Splatting (3DGS) framework that exploits the spatial coherence of 3D Gaussians for compact modeling of volumetric scenes. To this end, we first analyze the local coherence of 3D Gaussian attributes, and propose a novel locality-aware 3D Gaussian representation that effectively encodes locally-coherent Gaussian attributes using a neural field representation with a minimal storage requirement. On top of the novel representation, LocoGS is carefully designed with additional components such as dense initialization, an adaptive spherical harmonics bandwidth scheme and different encoding schemes for different Gaussian attributes to maximize compression performance. Experimental results demonstrate that our approach outperforms the rendering quality of existing compact Gaussian representations for representative real-world 3D datasets while achieving from 54.6$\times$ to 96.6$\times$ compressed storage size and from 2.1$\times$ to 2.4$\times$ rendering speed than 3DGS. Even our approach also demonstrates an averaged 2.4$\times$ higher rendering speed than the state-of-the-art compression method with comparable compression performance.

Hyeongmin Lee, Kyoungkook Kang, Jungseul Ok et al.

Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment. However, these approaches are constrained by intrinsic challenges of supervised learning. Primarily, the requirement for expertly-curated or retouched images escalates the data acquisition expenses. Moreover, their coverage of target style is confined to stylistic variants inferred from the training data. To surmount the above challenges, we propose an unsupervised learning-based approach for text-based image tone adjustment method, CLIPtone, that extends an existing image enhancement method to accommodate natural language descriptions. Specifically, we design a hyper-network to adaptively modulate the pretrained parameters of the backbone model based on text description. To assess whether the adjusted image aligns with the text description without ground truth image, we utilize CLIP, which is trained on a vast set of language-image pairs and thus encompasses knowledge of human perception. The major advantages of our approach are three fold: (i) minimal data collection expenses, (ii) support for a range of adjustments, and (iii) the ability to handle novel text descriptions unseen in training. Our approach's efficacy is demonstrated through comprehensive experiments, including a user study.

Daniel Feijoo, Paula Garrido-Mellado, Marcos V. Conde et al.

This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge, which aims to advance in efficient real-blur restoration. The challenge is based on a new test set based on the well known RSBlur dataset. Pairs of blur and degraded images in this dataset are captured using a double-camera system. Participant were tasked with developing solutions to effectively deblur these type of images while fulfilling strict efficiency constraints: fewer than 5 million model parameters and a computational budget under 200 GMACs. A total of 71 participants registered, with 4 teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers in efficient real-world image deblurring.

Kyoungkook Kang, Gyujin Sim, Geonung Kim et al.

Layers have become indispensable tools for professional artists, allowing them to build a hierarchical structure that enables independent control over individual visual elements. In this paper, we propose LayeringDiff, a novel pipeline for the synthesis of layered images, which begins by generating a composite image using an off-the-shelf image generative model, followed by disassembling the image into its constituent foreground and background layers. By extracting layers from a composite image, rather than generating them from scratch, LayeringDiff bypasses the need for large-scale training to develop generative capabilities for individual layers. Furthermore, by utilizing a pretrained off-the-shelf generative model, our method can produce diverse contents and object scales in synthesized layers. For effective layer decomposition, we adapt a large-scale pretrained generative prior to estimate foreground and background layers. We also propose high-frequency alignment modules to refine the fine-details of the estimated layers. Our comprehensive experiments demonstrate that our approach effectively synthesizes layered images and supports various practical applications.

Haechan Lee, Wonjoon Jin, Seung-Hwan Baek et al.

In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera images. Since recent stereo matching has demonstrated accurate geometry prediction, we introduce stereo matching into novel-view synthesis for high-quality geometry reconstruction. To this end, this paper proposes a novel framework, dubbed StereoNeRF, which integrates stereo matching into a NeRF-based generalizable view synthesis approach. StereoNeRF is equipped with three key components to effectively exploit stereo matching in novel-view synthesis: a stereo feature extractor, a depth-guided plane-sweeping, and a stereo depth loss. Moreover, we propose the StereoNVS dataset, the first multi-view dataset of stereo-camera images, encompassing a wide variety of both real and synthetic scenes. Our experimental results demonstrate that StereoNeRF surpasses previous approaches in generalizable view synthesis.

Heemin Yang, Jaesung Rim, Seungyong Lee et al.

In this paper, we present GyroDeblurNet, a novel single-image deblurring method that utilizes a gyro sensor to resolve the ill-posedness of image deblurring. The gyro sensor provides valuable information about camera motion that can improve deblurring quality. However, exploiting real-world gyro data is challenging due to errors from various sources. To handle these errors, GyroDeblurNet is equipped with two novel neural network blocks: a gyro refinement block and a gyro deblurring block. The gyro refinement block refines the erroneous gyro data using the blur information from the input image. The gyro deblurring block removes blur from the input image using the refined gyro data and further compensates for gyro error by leveraging the blur information from the input image. For training a neural network with erroneous gyro data, we propose a training strategy based on the curriculum learning. We also introduce a novel gyro data embedding scheme to represent real-world intricate camera shakes. Finally, we present both synthetic and real-world datasets for training and evaluating gyro-based single image deblurring. Our experiments demonstrate that our approach achieves state-of-the-art deblurring quality by effectively utilizing erroneous gyro data.

Hwayoon Lee, Kyoungkook Kang, Hyeongmin Lee et al.

Recent image restoration methods can be broadly categorized into two classes: (1) regression methods that recover the rough structure of the original image without synthesizing high-frequency details and (2) generative methods that synthesize perceptually-realistic high-frequency details even though the resulting image deviates from the original structure of the input. While both directions have been extensively studied in isolation, merging their benefits with a single framework has been rarely studied. In this paper, we propose UGPNet, a universal image restoration framework that can effectively achieve the benefits of both approaches by simply adopting a pair of an existing regression model and a generative model. UGPNet first restores the image structure of a degraded input using a regression model and synthesizes a perceptually-realistic image with a generative model on top of the regressed output. UGPNet then combines the regressed output and the synthesized output, resulting in a final result that faithfully reconstructs the structure of the original image in addition to perceptually-realistic textures. Our extensive experiments on deblurring, denoising, and super-resolution demonstrate that UGPNet can successfully exploit both regression and generative methods for high-fidelity image restoration.

Daneul Kim, Jingxu Zhang, Wonjoon Jin et al.

We propose to train a subject-driven customized video generation model through decoupling the subject-specific learning from temporal dynamics in zero-shot without additional tuning. A traditional method for video customization that is tuning-free often relies on large, annotated video datasets, which are computationally expensive and require extensive annotation. In contrast to the previous approach, we introduce the use of an image customization dataset directly on training video customization models, factorizing the video customization into two folds: (1) identity injection through image customization dataset and (2) temporal modeling preservation with a small set of unannotated videos through the image-to-video training method. Additionally, we employ random image token dropping with randomized image initialization during image-to-video fine-tuning to mitigate the copy-and-paste issue. To further enhance learning, we introduce stochastic switching during joint optimization of subject-specific and temporal features, mitigating catastrophic forgetting. Our method achieves strong subject consistency and scalability, outperforming existing video customization models in zero-shot settings, demonstrating the effectiveness of our framework.

Geonung Kim, Beomsu Kim, Eunhyeok Park et al.

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by these I2I models, their practical utility is hampered by their large model size and the computational burden of the iterative denoising process. In this paper, we propose a novel compression method tailored for diffusion-based I2I models. Based on the observations that the image conditions of I2I models already provide rich information on image structures, and that the time steps with a larger impact tend to be biased, we develop surprisingly simple yet effective approaches for reducing the model size and latency. We validate the effectiveness of our method on three representative I2I tasks: InstructPix2Pix for image editing, StableSR for image restoration, and ControlNet for image-conditional image generation. Our approach achieves satisfactory output quality with 39.2%, 56.4% and 39.2% reduction in model footprint, as well as 81.4%, 68.7% and 31.1% decrease in latency to InstructPix2Pix, StableSR and ControlNet, respectively.

Jaesung Rim, Junyong Lee, Heemin Yang et al.

Mobile cameras, despite their significant advancements, still have difficulty in low-light imaging due to compact sensors and lenses, leading to longer exposures and motion blur. Traditional blind deconvolution methods and learning-based deblurring methods can be potential solutions to remove blur. However, achieving practical performance still remains a challenge. To address this, we propose a learning-based deblurring framework for smartphones, utilizing wide and ultra-wide cameras as a hybrid camera system. We simultaneously capture a long-exposure wide image and short-exposure burst ultra-wide images, and utilize the burst images to deblur the wide image. To fully exploit burst ultra-wide images, we present HCDeblur, a practical deblurring framework that includes novel deblurring networks, HC-DNet and HC-FNet. HC-DNet utilizes motion information extracted from burst images to deblur a wide image, and HC-FNet leverages burst images as reference images to further enhance a deblurred output. For training and evaluating the proposed method, we introduce the HCBlur dataset, which consists of synthetic and real-world datasets. Our experiments demonstrate that HCDeblur achieves state-of-the-art deblurring quality. Code and datasets are available at https://cg.postech.ac.kr/research/HCDeblur.

Haeyun Choi, Heemin Yang, Janghyeok Han et al.

In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.

Tommoro Robotics, Jesoon Kang, Taegeon Park et al.

We introduce Habilis-$β$, a fast-motion and long-lasting on-device vision-language-action (VLA) model designed for real-world deployment. Current VLA evaluation remains largely confined to single-trial success rates under curated resets, which fails to capture the fast-motion and long-lasting capabilities essential for practical operation. To address this, we introduce the Productivity-Reliability Plane (PRP), which evaluates performance through Tasks per Hour (TPH) and Mean Time Between Intervention (MTBI) under a continuous-run protocol that demands both high-speed execution and sustained robustness. Habilis-$β$ achieves high performance by integrating language-free pre-training on large-scale play data for robust interaction priors with post-training on cyclic task demonstrations that capture state drift across consecutive task iterations. The system further employs ESPADA for phase-adaptive motion shaping to accelerate free-space transit, utilizes rectified-flow distillation to enable high-frequency control on edge devices, and incorporates classifier-free guidance (CFG) as a deployment-time knob to dynamically balance instruction adherence and learned interaction priors. In 1-hour continuous-run evaluations, Habilis-$β$ achieves strong performance under the PRP metrics, compared to $π_{0.5}$ in both simulation and real-world environments. In simulation, Habilis-$β$ achieves 572.6 TPH and 39.2 s MTBI (vs. 120.5 TPH and 30.5 s for $π_{0.5}$), while in a real-world humanoid logistics workflow it achieves 124 TPH and 137.4 s MTBI (vs. 19 TPH and 46.1 s for $π_{0.5}$). Finally, Habilis-$β$ achieves the highest reported performance on the standard RoboTwin 2.0 leaderboard across representative tasks, validating its effectiveness in complex manipulation scenarios.

Seungjoo Shin, Jaesik Park, Sunghyun Cho

Compression techniques for 3D Gaussian Splatting (3DGS) have recently achieved considerable success in minimizing storage overhead for 3D Gaussians while preserving high rendering quality. Despite the impressive storage reduction, the lack of learned priors restricts further advances in the rate-distortion trade-off for 3DGS compression tasks. To address this, we introduce a novel 3DGS compression framework that leverages the powerful representational capacity of learned image priors to recover compression-induced quality degradation. Built upon initially compressed Gaussians, our restoration network effectively models the compression artifacts in the image space between degraded and original Gaussians. To enhance the rate-distortion performance, we provide coarse rendering residuals into the restoration network as side information. By leveraging the supervision of restored images, the compressed Gaussians are refined, resulting in a highly compact representation with enhanced rendering performance. Our framework is designed to be compatible with existing Gaussian compression methods, making it broadly applicable across different baselines. Extensive experiments validate the effectiveness of our framework, demonstrating superior rate-distortion performance and outperforming the rendering quality of state-of-the-art 3DGS compression methods while requiring substantially less storage.

Janghyeok Han, Gyujin Sim, Geonung Kim et al.

Video super-resolution (VSR) aims to reconstruct a high-resolution (HR) video from a low-resolution (LR) counterpart. Achieving successful VSR requires producing realistic HR details and ensuring both spatial and temporal consistency. To restore realistic details, diffusion-based VSR approaches have recently been proposed. However, the inherent randomness of diffusion, combined with their tile-based approach, often leads to spatio-temporal inconsistencies. In this paper, we propose DC-VSR, a novel VSR approach to produce spatially and temporally consistent VSR results with realistic textures. To achieve spatial and temporal consistency, DC-VSR adopts a novel Spatial Attention Propagation (SAP) scheme and a Temporal Attention Propagation (TAP) scheme that propagate information across spatio-temporal tiles based on the self-attention mechanism. To enhance high-frequency details, we also introduce Detail-Suppression Self-Attention Guidance (DSSAG), a novel diffusion guidance scheme. Comprehensive experiments demonstrate that DC-VSR achieves spatially and temporally consistent, high-quality VSR results, outperforming previous approaches.

Sunung Mun, Jinhwan Nam, Sunghyun Cho et al.

Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a critical problem: attribute leakage, where edits meant for specific objects unintentionally affect unrelated regions or other target objects. Our analysis reveals the root cause as the semantic entanglement inherent in End-of-Sequence (EOS) embeddings generated by autoregressive text encoders, which indiscriminately aggregate attributes across prompts. To address this issue, we introduce Attribute-Leakage-free Editing (ALE), a framework that tackles attribute leakage at its source. ALE combines Object-Restricted Embeddings (ORE) to disentangle text embeddings, Region-Guided Blending for Cross-Attention Masking (RGB-CAM) for spatially precise attention, and Background Blending (BB) to preserve non-edited content. To quantitatively evaluate attribute leakage across various editing methods, we propose the Attribute-Leakage Evaluation Benchmark (ALE-Bench), featuring comprehensive editing scenarios and new metrics. Extensive experiments show that ALE reduces attribute leakage by large margins, thereby enabling accurate, multi-object, text-driven image editing while faithfully preserving non-target content.

Sanghyun Kim, Min Jung Lee, Woohyeok Kim et al.

Burst image super-resolution has been a topic of active research in recent years due to its ability to obtain a high-resolution image by using complementary information between multiple frames in the burst. In this work, we explore using burst shots with non-uniform exposures to confront real-world practical scenarios by introducing a new benchmark dataset, dubbed Non-uniformly Exposed Burst Image (NEBI), that includes the burst frames at varying exposure times to obtain a broader range of irradiance and motion characteristics within a scene. As burst shots with non-uniform exposures exhibit varying levels of degradation, fusing information of the burst shots into the first frame as a base frame may not result in optimal image quality. To address this limitation, we propose a Frame Selection Network (FSN) for non-uniform scenarios. This network seamlessly integrates into existing super-resolution methods in a plug-and-play manner with low computational costs. The comparative analysis reveals the effectiveness of the nonuniform setting for the practical scenario and our FSN on synthetic-/real- NEBI datasets.

Kiyeon Kim, Seungyong Lee, Sunghyun Cho

Most of traditional single image deblurring methods before deep learning adopt a coarse-to-fine scheme that estimates a sharp image at a coarse scale and progressively refines it at finer scales. While this scheme has also been adopted to several deep learning-based approaches, recently a number of single-scale approaches have been introduced showing superior performance to previous coarse-to-fine approaches both in quality and computation time. In this paper, we revisit the coarse-to-fine scheme, and analyze defects of previous coarse-to-fine approaches that degrade their performance. Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring that adopts our remedies to the defects. Specifically, MSSNet adopts three novel technical components: stage configuration reflecting blur scales, an inter-scale information propagation scheme, and a pixel-shuffle-based multi-scale scheme. Our experiments show that MSSNet achieves the state-of-the-art performance in terms of quality, network size, and computation time.

Jaesung Rim, Geonung Kim, Jungeon Kim et al.

Training learning-based deblurring methods demands a tremendous amount of blurred and sharp image pairs. Unfortunately, existing synthetic datasets are not realistic enough, and deblurring models trained on them cannot handle real blurred images effectively. While real datasets have recently been proposed, they provide limited diversity of scenes and camera settings, and capturing real datasets for diverse settings is still challenging. To resolve this, this paper analyzes various factors that introduce differences between real and synthetic blurred images. To this end, we present RSBlur, a novel dataset with real blurred images and the corresponding sharp image sequences to enable a detailed analysis of the difference between real and synthetic blur. With the dataset, we reveal the effects of different factors in the blur generation process. Based on the analysis, we also present a novel blur synthesis pipeline to synthesize more realistic blur. We show that our synthesis pipeline can improve the deblurring performance on real blurred images.

Jinwoo Lee, Hyunsung Go, Hyunjoon Lee et al.

Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 benchmark datasets.

Junyong Lee, Hyeongseok Son, Jaesung Rim et al.

We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) that is specifically designed to handle spatially-varying and large defocus blur. For adaptively handling spatially-varying blur, IFAN predicts pixel-wise deblurring filters, which are applied to defocused features of an input image to generate deblurred features. For effectively managing large blur, IFAN models deblurring filters as stacks of small-sized separable filters. Predicted separable deblurring filters are applied to defocused features using a novel Iterative Adaptive Convolution (IAC) layer. We also propose a training scheme based on defocus disparity estimation and reblurring, which significantly boosts the deblurring quality. We demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively on real-world images.

Jaebong Jeong, Janghun Jo, Jingdong Wang et al.

Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have geometrically invalid contents. To provide users with rich controllability on synthesized images in the aspect of 3D geometry, we propose a novel approach to realistic-looking image synthesis based on a configurable 3D scene layout. Our approach takes a 3D scene with semantic class labels as input and trains a 3D scene painting network that synthesizes color values for the input 3D scene. With the trained painting network, realistic-looking images for the input 3D scene can be rendered and manipulated. To train the painting network without 3D color supervision, we exploit an off-the-shelf 2D semantic image synthesis method. In experiments, we show that our approach produces images with geometrically correct structures and supports geometric manipulation such as the change of the viewpoint and object poses as well as manipulation of the painting style.

Hyeongseok Son, Junyong Lee, Jonghyeop Lee et al.

For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames. First, we present blur-invariant motion estimation learning to improve motion estimation accuracy between blurry frames. Second, for motion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors. We combine these two processes to propose an effective recurrent video deblurring network that fully exploits deblurred previous frames. Experiments show that our method achieves the state-of-the-art performance both quantitatively and qualitatively compared to recent methods that use deep learning.

Hyeongseok Son, Junyong Lee, Sunghyun Cho et al.

This paper proposes a novel deep learning approach for single image defocus deblurring based on inverse kernels. In a defocused image, the blur shapes are similar among pixels although the blur sizes can spatially vary. To utilize the property with inverse kernels, we exploit the observation that when only the size of a defocus blur changes while keeping the shape, the shape of the corresponding inverse kernel remains the same and only the scale changes. Based on the observation, we propose a kernel-sharing parallel atrous convolutional (KPAC) block specifically designed by incorporating the property of inverse kernels for single image defocus deblurring. To effectively simulate the invariant shapes of inverse kernels with different scales, KPAC shares the same convolutional weights among multiple atrous convolution layers. To efficiently simulate the varying scales of inverse kernels, KPAC consists of only a few atrous convolution layers with different dilations and learns per-pixel scale attentions to aggregate the outputs of the layers. KPAC also utilizes the shape attention to combine the outputs of multiple convolution filters in each atrous convolution layer, to deal with defocus blur with a slightly varying shape. We demonstrate that our approach achieves state-of-the-art performance with a much smaller number of parameters than previous methods.

Kyoungkook Kang, Seongtae Kim, Sunghyun Cho

For successful semantic editing of real images, it is critical for a GAN inversion method to find an in-domain latent code that aligns with the domain of a pre-trained GAN model. Unfortunately, such in-domain latent codes can be found only for in-range images that align with the training images of a GAN model. In this paper, we propose BDInvert, a novel GAN inversion approach to semantic editing of out-of-range images that are geometrically unaligned with the training images of a GAN model. To find a latent code that is semantically editable, BDInvert inverts an input out-of-range image into an alternative latent space than the original latent space. We also propose a regularized inversion method to find a solution that supports semantic editing in the alternative space. Our experiments show that BDInvert effectively supports semantic editing of out-of-range images with geometric transformations.

Seunghun Lee, Sunghyun Cho, Sunghoon Im

In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. Unlike the existing domain adaptation methods that learn associated features sharing a domain, DRANet preserves the distinctiveness of each domain's characteristics. Our model encodes individual representations of content (scene structure) and style (artistic appearance) from both source and target images. Then, it adapts the domain by incorporating the transferred style factor into the content factor along with learnable weights specified for each domain. This learning framework allows bi-/multi-directional domain adaptation with a single encoder-decoder network and aligns their domain shift. Additionally, we propose a content-adaptive domain transfer module that helps retain scene structure while transferring style. Extensive experiments show our model successfully separates content-style factors and synthesizes visually pleasing domain-transferred images. The proposed method demonstrates state-of-the-art performance on standard digit classification tasks as well as semantic segmentation tasks.

Taeyoung Son, Juwon Kang, Namyup Kim et al.

Despite the great advances in visual recognition, it has been witnessed that recognition models trained on clean images of common datasets are not robust against distorted images in the real world. To tackle this issue, we present a Universal and Recognition-friendly Image Enhancement network, dubbed URIE, which is attached in front of existing recognition models and enhances distorted input to improve their performance without retraining them. URIE is universal in that it aims to handle various factors of image degradation and to be incorporated with any arbitrary recognition models. Also, it is recognition-friendly since it is optimized to improve the robustness of following recognition models, instead of perceptual quality of output image. Our experiments demonstrate that URIE can handle various and latent image distortions and improve the performance of existing models for five diverse recognition tasks when input images are degraded.

Jiwoon Ahn, Sunghyun Cho, Suha Kwak

This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision. Our approach generates pseudo instance segmentation labels of training images, which are used to train a fully supervised model. For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate boundaries. To this end, we propose IRNet, which estimates rough areas of individual instances and detects boundaries between different object classes. It thus enables to assign instance labels to the seeds and to propagate them within the boundaries so that the entire areas of instances can be estimated accurately. Furthermore, IRNet is trained with inter-pixel relations on the attention maps, thus no extra supervision is required. Our method with IRNet achieves an outstanding performance on the PASCAL VOC 2012 dataset, surpassing not only previous state-of-the-art trained with the same level of supervision, but also some of previous models relying on stronger supervision.

Jeehyeong Kim, Joohan Park, Jaewon Noh et al.

For Device-to-device (D2D) communication of Internet-of-Things (IoT) enabled 5G system, there is a limit to allocating resources considering a complicated interference between different links in a centralized manner. If D2D link is controlled by an enhanced node base station (eNB), and thus, remains a burden on the eNB and it causes delayed latency. This paper proposes a fully autonomous power allocation method for IoT-D2D communication underlaying cellular networks using deep learning. In the proposed scheme, an IoT-D2D transmitter decides the transmit power independently from an eNB and other IoT-D2D devices. In addition, the power set can be nearly optimized by deep learning with distributed manner to achieve higher cell throughput. We present a distributed deep learning architecture in which the devices are trained as a group but operate independently. The deep learning can attain near optimal cell throughput while suppressing interference to eNB.