Author name cluster

In So Kweon

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers

1 author row

TMLR Journal 2025 Journal Article

Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

Inkyu Shin
Qihang Yu
Xiaohui Shen
In So Kweon
Kuk-Jin Yoon
Liang-Chieh Chen

Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address this, we introduce Video-3DGS, a 3D Gaussian Splatting (3DGS)-based video refiner designed to enhance temporal consistency in zero-shot video editors. Our approach utilizes a two-stage 3D Gaussian optimizing process tailored for editing dynamic monocular videos. In the first stage, Video-3DGS employs an improved version of COLMAP, referred to as MC-COLMAP, which processes original videos using a Masked and Clipped approach. For each video clip, MC-COLMAP generates the point clouds for dynamic foreground objects and complex backgrounds. These point clouds are utilized to initialize two sets of 3D Gaussians (Frg-3DGS and Bkg-3DGS) aiming to represent foreground and background views. Both foreground and background views are then merged with a 2D learnable parameter map to reconstruct full views. In the second stage, we leverage the reconstruction ability developed in the first stage to impose the temporal constraints on the video diffusion model. This approach ensures the temporal consistency in the edited videos while maintaining high fidelity to the editing text prompt. We further propose a recursive and ensembled refinement by revisiting the denoising step and guidance scale used in video diffusion process with Video-3DGS. To demonstrate the efficacy of Video-3DGS on both stages, we conduct extensive experiments across two related tasks: Video Reconstruction and Video Editing. Video-3DGS trained with 3k iterations significantly improves video reconstruction quality (+3 PSNR, +7 PSNR increase) and training efficiency (×1.9, ×4.5 times faster) over NeRF-based and 3DGS-based state-of-art methods on DAVIS dataset, respectively. Moreover, it enhances video editing by ensuring temporal consistency across 58 dynamic monocular videos.

NeurIPS Conference 2025 Conference Paper

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

Chenshuang Zhang
Kang Zhang
Joon Son Chung
In So Kweon
Junmo Kim
Chengzhi Mao

Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting their scalability and generalization without extensive labeled data. We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training. This ability arises because their denoising process isolates motion in early, high-noise stages, distinct from later appearance refinement. Capitalizing on this discovery, our self-supervised tracker significantly improves performance in distinguishing visually similar objects, an underexplored failure point for existing methods. Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks and our newly introduced tests focused on tracking visually similar items. Visualizations confirm that these diffusion-derived motion representations enable robust tracking of even identical objects across challenging viewpoint changes and deformations. Project page: \small{\url{https: //chenshuang-zhang. github. io/projects/ted}}.

TMLR Journal 2024 Journal Article

Towards Understanding Dual BN In Hybrid Adversarial Training

Chenshuang Zhang
Chaoning Zhang
Kang Zhang
Axi Niu
Junmo Kim
In So Kweon

There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean samples are from two different domains, a common practice in prior works is to adopt Dual BN, where BN$_{adv}$ and BN$_{clean}$ are used for adversarial and clean branches, respectively. A popular belief for motivating Dual BN is that estimating normalization statistics of this mixture distribution is challenging and thus disentangling it for normalization achieves stronger robustness. In contrast to this belief, we reveal that disentangling statistics plays a less role than disentangling affine parameters in model training. This finding aligns with prior work (Rebuffi et al., 2023), and we build upon their research for further investigations. We demonstrate that the domain gap between adversarial and clean samples is not very large, which is counter-intuitive considering the significant influence of adversarial perturbation on the model accuracy. We further propose a two-task hypothesis which serves as the empirical foundation and a unified framework for Hybrid-AT improvement. We also investigate Dual BN in test-time and reveal that affine parameters characterize the robustness during inference. Overall, our work sheds new light on understanding the mechanism of Dual BN in Hybrid-AT and its underlying justification.

IJCAI Conference 2023 Conference Paper

A Survey on Masked Autoencoder for Visual Self-supervised Learning

Chaoning Zhang
Chenshuang Zhang
Junha Song
John Seon Keun Yi
In So Kweon

With the increasing popularity of masked autoencoders, self-supervised learning (SSL) in vision undertakes a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction have become a de facto standard SSL practice in NLP (e. g. , BERT). By contrast, early attempts at generative methods in vision have been outperformed by their discriminative counterparts (like contrastive learning). However, the success of masked image modeling has revived the autoencoder-based visual pretraining method. As a milestone to bridge the gap with BERT in NLP, masked autoencoder in vision has attracted unprecedented attention. This work conducts a survey on masked autoencoders for visual SSL.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

Daehan Kim
Minseok Seo
Kwanyong Park
Inkyu Shin
Sanghyun Woo
In So Kweon
Dong-Geol Choi

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target samples to obtain domain-mixed samples for better adaptation. However, the extension of the idea from classification to segmentation (i.e., structured output) is nontrivial. This paper systematically studies the impact of mixup under the domain adaptive semantic segmentation task and presents a simple yet effective mixup strategy called Bidirectional Domain Mixup (BDM). In specific, we achieve domain mixup in two-step: cut and paste. Given the warm-up model trained from any adaptation techniques, we forward the source and target samples and perform a simple threshold-based cut out of the unconfident regions (cut). After then, we fill-in the dropped regions with the other domain region patches (paste). In doing so, we jointly consider class distribution, spatial structure, and pseudo label confidence. Based on our analysis, we found that BDM leaves domain transferable regions by cutting, balances the dataset-level class distribution while preserving natural scene context by pasting. We coupled our proposal with various state-of-the-art adaptation models and observe significant improvement consistently. We also provide extensive ablation experiments to empirically verify our main components of the framework. Visit our project page with the code at https://sites.google.com/view/bidirectional-domain-mixup

PDF Details DOI

IJCAI Conference 2021 Conference Paper

A Survey on Universal Adversarial Attack

Chaoning Zhang
Philipp Benz
Chenguo Lin
Adil Karjauv
Jing Wu
In So Kweon

The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i. e. a single perturbation to fool the target DNN for most images. With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. We aim to extend this work as a dynamic survey that will regularly update its content to follow new works regarding UAP or universal attack in a wide range of domains, such as image, audio, video, text, etc. Relevant updates will be discussed at: https: //bit. ly/2SbQlLG. We welcome authors of future works in this field to contact us for including your new findings.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency

Seokju Lee
Sunghoon Im
Stephen Lin
In So Kweon

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion, and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are publicly available.

AAAI Conference 2021 Conference Paper

Motion-blurred Video Interpolation and Extrapolation

Dawit Mureja Argaw
Junsik Kim
Francois Rameau
In So Kweon

Abrupt motion of camera or objects in a scene result in a blurry video, and therefore recovering high quality video requires two types of enhancements: visual enhancement and temporal upsampling. A broad range of research attempted to recover clean frames from blurred image sequences or temporally upsample frames by interpolation, yet there are very limited studies handling both problems jointly. In this work, we present a novel framework for deblurring, interpolating and extrapolating sharp frames from a motion-blurred video in an end-to-end manner. We design our framework by first learning the pixel-level motion that caused the blur from the given inputs via optical flow estimation and then predict multiple clean frames by warping the decoded features with the estimated flows. To ensure temporal coherence across predicted frames and address potential temporal ambiguity, we propose a simple, yet effective flow-based rule. The effectiveness and favorability of our approach are highlighted through extensive qualitative and quantitative evaluations on motionblurred datasets from high speed videos.

AAAI Conference 2021 Conference Paper

Optical Flow Estimation from a Single Motion-blurred Image

Dawit Mureja Argaw
Junsik Kim
Francois Rameau
Jae Won Cho
In So Kweon

In most of computer vision applications, motion blur is regarded as an undesirable artifact. However, it has been shown that motion blur in an image may have practical interests in fundamental computer vision problems. In this work, we propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner. We design our network with transformer networks to learn globally and locally varying motions from encoded features of a motion-blurred input, and decode left and right frame features without explicit frame supervision. A flow estimator network is then used to estimate optical flow from the decoded features in a coarse-to-fine manner. We qualitatively and quantitatively evaluate our model through a large set of experiments on synthetic and real motion-blur datasets. We also provide in-depth analysis of our model in connection with related approaches to highlight the effectiveness and favorability of our approach. Furthermore, we showcase the applicability of the flow estimated by our method on deblurring and moving object segmentation tasks.

AAAI Conference 2021 Conference Paper

Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards a Fourier Perspective

Chaoning Zhang
Philipp Benz
Adil Karjauv
In So Kweon

The booming interest in adversarial attacks stems from a misalignment between human vision and a deep neural network (DNN), i. e. a human imperceptible perturbation fools the DNN. Moreover, a single perturbation, often called universal adversarial perturbation (UAP), can be generated to fool the DNN for most images. A similar misalignment phenomenon has also been observed in the deep steganography task, where a decoder network can retrieve a secret image back from a slightly perturbed cover image. We attempt explaining the success of both in a unified manner from the Fourier perspective. We perform task-specific and joint analysis and reveal that (a) frequency is a key factor that influences their performance based on the proposed entropy metric for quantifying the frequency distribution; (b) their success can be attributed to a DNN being highly sensitive to high-frequency content. We also perform feature layer analysis for providing deep insight on model generalization and robustness. Additionally, we propose two new variants of universal perturbations: (1) high-pass UAP (HP-UAP) being less visible to the human eye; (2) Universal Secret Adversarial Perturbation (USAP) that simultaneously achieves attack and hiding.

NeurIPS Conference 2020 Conference Paper

An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

Kyunghyun Lee
Byeong-Uk Lee
Ukcheol Shin
In So Kweon

Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, with DRL having good sample efficiency and poor stability, while ES being vice versa. Recently, there have been attempts to combine these algorithms, but these methods fully rely on synchronous update scheme, making it not ideal to maximize the benefits of the parallelism in ES. To solve this challenge, asynchronous update scheme was introduced, which is capable of good time-efficiency and diverse policy exploration. In this paper, we introduce an Asynchronous Evolution Strategy-Reinforcement Learning (AES-RL) that maximizes the parallel efficiency of ES and integrates it with policy gradient methods. Specifically, we propose 1) a novel framework to merge ES and DRL asynchronously and 2) various asynchronous update methods that can take all advantages of asynchronism, ES, and DRL, which are exploration and time efficiency, stability, and sample efficiency, respectively. The proposed framework and update methods are evaluated in continuous control benchmark work, showing superior performance as well as time efficiency compared to the previous methods.

NeurIPS Conference 2020 Conference Paper

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Kwanyong Park
Sanghyun Woo
Inkyu Shin
In So Kweon

Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently, as it could be beneficial for various label-scarce real-world scenarios (e. g. , robot control, autonomous driving, medical imaging, etc. ). Despite the significant progress in this field, current works mainly focus on a single-source single-target setting, which cannot handle more practical settings of multiple targets or even unseen targets. In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. We present a novel framework based on three main design principles: discover, hallucinate, and adapt. The scheme first clusters compound target data based on style, discovering multiple latent domains (discover). Then, it hallucinates multiple latent target domains in source by using image-translation (hallucinate). This step ensures the latent domains in the source and the target to be paired. Finally, target-to-source alignment is learned separately between domains (adapt). In high-level, our solution replaces a hard OCDA problem with much easier multiple UDA problems. We evaluate our solution on standard benchmark GTA to C-driving, and achieved new state-of-the-art results.

AAAI Conference 2020 Conference Paper

Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling

Yunjae Jung
Dahun Kim
Sanghyun Woo
Kyungsu Kim
Sungjin Kim
In So Kweon

Visual storytelling is a task of creating a short story based on photo streams. Unlike existing visual captioning, storytelling aims to contain not only factual descriptions, but also humanlike narration and semantics. However, the VIST dataset consists only of a small, ﬁxed number of photos per story. Therefore, the main challenge of visual storytelling is to ﬁll in the visual gap between photos with narrative and imaginative story. In this paper, we propose to explicitly learn to imagine a storyline that bridges the visual gap. During training, one or more photos is randomly omitted from the input stack, and we train the network to produce a full plausible story even with missing photo(s). Furthermore, we propose for visual storytelling a hide-and-tell model, which is designed to learn nonlocal relations across the photo streams and to reﬁne and improve conventional RNN-based models. In experiments, we show that our scheme of hide-and-tell, and the network design are indeed effective at storytelling, and that our model outperforms previous state-of-the-art methods in automatic metrics. Finally, we qualitatively show the learned ability to interpolate storyline over visual gaps.

NeurIPS Conference 2020 Conference Paper

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Chaoning Zhang
Philipp Benz
Adil Karjauv
Geng Sun
In So Kweon

Neural networks have been shown effective in deep steganography for hiding a full image in another. However, the reason for its success remains not fully clear. Under the existing cover ($C$) dependent deep hiding (DDH) pipeline, it is challenging to analyze how the secret ($S$) image is encoded since the encoded message cannot be analyzed independently. We propose a novel universal deep hiding (UDH) meta-architecture to disentangle the encoding of $S$ from $C$. We perform extensive analysis and demonstrate that the success of deep steganography can be attributed to a frequency discrepancy between $C$ and the encoded secret image. Despite $S$ being hidden in a cover-agnostic manner, strikingly, UDH achieves a performance comparable to the existing DDH. Beyond hiding one image, we push the limits of deep steganography. Exploiting its property of being \emph{universal}, we propose universal watermarking as a timely solution to address the concern of the exponentially increasing amount of images/videos. UDH is robust to a pixel intensity shift on the container image, which makes it suitable for challenging application of light field messaging (LFM). This is the first work demonstrating the success of (DNN-based) hiding a full image for watermarking and LFM. Code: \url{https: //github. com/ChaoningZhang/Universal-Deep-Hiding}

AAAI Conference 2019 Conference Paper

Discriminative Feature Learning for Unsupervised Video Summarization

Yunjae Jung
Donghyeon Cho
Dahun Kim
Sanghyun Woo
In So Kweon

In this paper, we address the problem of unsupervised video summarization that automatically extracts key-shots from an input video. Specifically, we tackle two critical issues based on our empirical observations: (i) Ineffective feature learning due to flat distributions of output importance scores for each frame, and (ii) training difficulty when dealing with longlength video inputs. To alleviate the first problem, we propose a simple yet effective regularization loss term called variance loss. The proposed variance loss allows a network to predict output scores for each frame with high discrepancy which enables effective feature learning and significantly improves model performance. For the second problem, we design a novel two-stream network named Chunk and Stride Network (CSNet) that utilizes local (chunk) and global (stride) temporal view on the video features. Our CSNet gives better summarization results for long-length videos compared to the existing methods. In addition, we introduce an attention mechanism to handle the dynamic information in videos. We demonstrate the effectiveness of the proposed methods by conducting extensive ablation studies and show that our final model achieves new state-of-the-art results on two benchmark datasets.

AAAI Conference 2019 Conference Paper

Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles

Dahun Kim
Donghyeon Cho
In So Kweon

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream of study extends to video domain where the cost of human labeling is even more expensive. However, the most of existing methods are still based on 2D CNN architectures that can not directly capture spatio-temporal information for video applications. In this paper, we introduce a new self-supervised task called as Space-Time Cubic Puzzles to train 3D CNNs using large scale video dataset. This task requires a network to arrange permuted 3D spatio-temporal crops. By completing Space-Time Cubic Puzzles, the network learns both spatial appearance and temporal relation of video frames, which is our final goal. In experiments, we demonstrate that our learned 3D representation is well transferred to action recognition tasks, and outperforms state-of-the-art 2D CNN-based competitors on UCF101 and HMDB51 datasets.

AAAI Conference 2018 Conference Paper

Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition

Junsik Kim
Seokju Lee
Tae-Hyun Oh
In So Kweon

Recent advances in visual recognition show overarching success by virtue of large amounts of supervised data. However, the acquisition of a large supervised dataset is often challenging. This is also true for intelligent transportation applications, i. e. , trafﬁc sign recognition. For example, a model trained with data of one country may not be easily generalized to another country without much data. We propose a novel feature embedding scheme for unseen class classiﬁcation when the representative class template is given. Trafﬁc signs, unlike other objects, have ofﬁcial images. We perform co-domain embedding using a quadruple relationship from real and synthetic domains. Our quadruplet network fully utilizes the explicit pairwise similarity relationships among samples from different domains. We validate our method on three datasets with two experiments involving one-shot classiﬁcation and feature generalization. The results show that the proposed method outperforms competing approaches on both seen and unseen classes.

NeurIPS Conference 2018 Conference Paper

LinkNet: Relational Embedding for Scene Graph

Sanghyun Woo
Dahun Kim
Donghyeon Cho
In So Kweon

Objects and their relationships are critical contents for image understanding. A scene graph provides a structured description that captures these properties of an image. However, reasoning about the relationships between objects is very challenging and only a few recent works have attempted to solve the problem of generating a scene graph from an image. In this paper, we present a novel method that improves scene graph generation by explicitly modeling inter-dependency among the entire object instances. We design a simple and effective relational embedding module that enables our model to jointly represent connections among all related objects, rather than focus on an object in isolation. Our novel method significantly benefits two main parts of the scene graph generation task: object classification and relationship classification. Using it on top of a basic Faster R-CNN, our model achieves state-of-the-art results on the Visual Genome benchmark. We further push the performance by introducing global context encoding module and geometrical layout encoding module. We validate our final model, LinkNet, through extensive ablation studies, demonstrating its efficacy in scene graph generation.

AAAI Conference 2018 Conference Paper

Multispectral Transfer Network: Unsupervised Depth Estimation for All-Day Vision

Namil Kim
Yukyung Choi
Soonmin Hwang
In So Kweon

To understand the real-world, it is essential to perceive in all-day conditions including cases which are not suitable for RGB sensors, especially at night. Beyond these limitations, the innovation introduced here is a multispectral solution in the form of depth estimation from a thermal sensor without an additional depth sensor. Based on an analysis of multispectral properties and the relevance to depth predictions, we propose an efﬁcient and novel multi-task framework called the Multispectral Transfer Network (MTN) to estimate a depth image from a single thermal image. By exploiting geometric priors and chromaticity clues, our model can generate a pixel-wise depth image in an unsupervised manner. Moreover, we propose a new type of multitask module called Interleaver as a means of incorporating the chromaticity and ﬁne details of skip-connections into the depth estimation framework without sharing feature layers. Lastly, we explain a novel technical means of stably training and covering large disparities and extending thermal images to data-driven methods for all-day conditions. In experiments, we demonstrate the better performance and generalization of depth estimation through the proposed multispectral stereo dataset, including various driving conditions.