Sangyoun Lee

Dogyoon Lee, Minhyeok Lee, Chajin Shin et al.

Neural Radiance Field (NeRF) has exhibited outstanding three-dimensional (3D) reconstruction quality via the novel view synthesis from multi-view images and paired calibrated camera parameters. However, previous NeRF-based systems have been demonstrated under strictly controlled settings, with little attention paid to less ideal scenarios, including with the presence of noise such as exposure, illumination changes, and blur. In particular, though blur frequently occurs in real situations, NeRF that can handle blurred images has received little attention. The few studies that have investigated NeRF for blurred images have not considered geometric and appearance consistency in 3D space, which is one of the most important factors in 3D reconstruction. This leads to inconsistency and the degradation of the perceptual quality of the constructed scene. Hence, this paper proposes a DP-NeRF, a novel clean NeRF framework for blurred images, which is constrained with two physical priors. These priors are derived from the actual blurring process during image acquisition by the camera. DP-NeRF proposes rigid blurring kernel to impose 3D consistency utilizing the physical priors and adaptive weight proposal to refine the color composition error in consideration of the relationship between depth and blur. We present extensive experimental results for synthetic and real scenes with two types of blur: camera motion blur and defocus blur. The results demonstrate that DP-NeRF successfully improves the perceptual quality of the constructed NeRF ensuring 3D geometric and appearance consistency. We further demonstrate the effectiveness of our model with comprehensive ablation analysis.

Minhyeok Lee, Chaewon Park, Suhwan Cho et al.

RGB-D salient object detection (SOD) has been in the spotlight recently because it is an important preprocessing operation for various vision tasks. However, despite advances in deep learning-based methods, RGB-D SOD is still challenging due to the large domain gap between an RGB image and the depth map and low-quality depth maps. To solve this problem, we propose a novel superpixel prototype sampling network (SPSN) architecture. The proposed model splits the input RGB image and depth map into component superpixels to generate component prototypes. We design a prototype sampling network so that the network only samples prototypes corresponding to salient objects. In addition, we propose a reliance selection module to recognize the quality of each RGB and depth feature map and adaptively weight them in proportion to their reliability. The proposed method makes the model robust to inconsistencies between RGB images and depth maps and eliminates the influence of non-salient objects. Our method is evaluated on five popular datasets, achieving state-of-the-art performance. We prove the effectiveness of the proposed method through comparative experiments.

Minhyeok Lee, Suhwan Cho, Seunghoon Lee et al.

Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video sequence. This difficulty can be solved by using motion information such as optical flow, but using only the information between adjacent frames results in poor connectivity between distant frames and poor performance. To solve this problem, we propose a novel prototype memory network architecture. The proposed model effectively extracts the RGB and motion information by extracting superpixel-based component prototypes from the input RGB images and optical flow maps. In addition, the model scores the usefulness of the component prototypes in each frame based on a self-learning algorithm and adaptively stores the most useful prototypes in memory and discards obsolete prototypes. We use the prototypes in the memory bank to predict the next query frames mask, which enhances the association between distant frames to help with accurate mask prediction. Our method is evaluated on three datasets, achieving state-of-the-art performance. We prove the effectiveness of the proposed model with various ablation studies.

Suhwan Cho, Minhyeok Lee, Seunghoon Lee et al.

Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level. In unsupervised VOS, most state-of-the-art methods leverage motion cues obtained from optical flow maps in addition to appearance cues to exploit the property that salient objects usually have distinctive movements compared to the background. However, as they are overly dependent on motion cues, which may be unreliable in some cases, they cannot achieve stable prediction. To reduce this motion dependency of existing two-stream VOS methods, we propose a novel motion-as-option network that optionally utilizes motion cues. Additionally, to fully exploit the property of the proposed network that motion is not always required, we introduce a collaborative network learning strategy. On all the public benchmark datasets, our proposed network affords state-of-the-art performance with real-time inference speed.

Donghyeong Kim, Chaewon Park, Suhwan Cho et al.

Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some methods do not meet the speed requirements of real-time inference, which is crucial for real-world applications. To address this issue, we propose a new method called Fast Adaptive Patch Memory (FAPM) for real-time industrial anomaly detection. FAPM utilizes patch-wise and layer-wise memory banks that store the embedding features of images at the patch and layer level, respectively, which eliminates unnecessary repetitive computations. We also propose patch-wise adaptive coreset sampling for faster and more accurate detection. FAPM performs well in both accuracy and speed compared to other state-of-the-art methods

Jungho Lee, Minhyeok Lee, Dogyoon Lee et al.

Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-based action recognition and have achieved remarkable performance. Generating adjacency matrices with semantically meaningful edges is particularly important for this task, but extracting such edges is challenging problem. To solve this, we propose a hierarchically decomposed graph convolutional network (HD-GCN) architecture with a novel hierarchically decomposed graph (HD-Graph). The proposed HD-GCN effectively decomposes every joint node into several sets to extract major structurally adjacent and distant edges, and uses them to construct an HD-Graph containing those edges in the same semantic spaces of a human skeleton. In addition, we introduce an attention-guided hierarchy aggregation (A-HA) module to highlight the dominant hierarchical edge sets of the HD-Graph. Furthermore, we apply a new six-way ensemble method, which uses only joint and bone stream without any motion stream. The proposed model is evaluated and achieves state-of-the-art performance on four large, popular datasets. Finally, we demonstrate the effectiveness of our model with various comparative experiments.

Suhwan Cho, Heansung Lee, Minhyeok Lee et al.

Semi-supervised video object segmentation (VOS) aims to densely track certain designated objects in videos. One of the main challenges in this task is the existence of background distractors that appear similar to the target objects. We propose three novel strategies to suppress such distractors: 1) a spatio-temporally diversified template construction scheme to obtain generalized properties of the target objects; 2) a learnable distance-scoring function to exclude spatially-distant distractors by exploiting the temporal consistency between two consecutive frames; 3) swap-and-attach augmentation to force each object to have unique features by providing training samples containing entangled objects. On all public benchmark datasets, our model achieves a comparable performance to contemporary state-of-the-art approaches, even with real-time performance. Qualitative results also demonstrate the superiority of our approach over existing methods. We believe our approach will be widely used for future VOS research.

Taeoh Kim, Jinhyung Kim, Minho Shim et al.

Data augmentation has recently emerged as an essential component of modern training recipes for visual recognition tasks. However, data augmentation for video recognition has been rarely explored despite its effectiveness. Few existing augmentation recipes for video recognition naively extend the image augmentation methods by applying the same operations to the whole video frames. Our main idea is that the magnitude of augmentation operations for each frame needs to be changed over time to capture the real-world video's temporal variations. These variations should be generated as diverse as possible using fewer additional hyper-parameters during training. Through this motivation, we propose a simple yet effective video data augmentation framework, DynaAugment. The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations. DynaAugment also includes an extended search space suitable for video for automatic data augmentation methods. DynaAugment experimentally demonstrates that there are additional performance rooms to be improved from static augmentations on diverse video models. Specifically, we show the effectiveness of DynaAugment on various video datasets and tasks: large-scale video recognition (Kinetics-400 and Something-Something-v2), small-scale video recognition (UCF- 101 and HMDB-51), fine-grained video recognition (Diving-48 and FineGym), video action segmentation on Breakfast, video action localization on THUMOS'14, and video object detection on MOT17Det. DynaAugment also enables video models to learn more generalized representation to improve the model robustness on the corrupted videos.

Minjung Kim, MyeongAh Cho, Heansung Lee et al.

Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes. In addition to the processes performed during holistic person Re-ID, occluded person Re-ID involves the removal of obstacles and the detection of partially visible body parts. Most existing methods utilize the off-the-shelf pose or parsing networks as pseudo labels, which are prone to error. To address these issues, we propose a novel Occlusion Correction Network (OCNet) that corrects features through relational-weight learning and obtains diverse and representative features without using external networks. In addition, we present a simple concept of a center feature in order to provide an intuitive solution to pedestrian occlusion scenarios. Furthermore, we suggest the idea of Separation Loss (SL) for focusing on different parts between global features and part features. We conduct extensive experiments on five challenging benchmark datasets for occluded and holistic Re-ID tasks to demonstrate that our method achieves superior performance to state-of-the-art methods especially on occluded scene.

Jungho Lee, Minhyeok Lee, Suhwan Cho et al.

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body's skeletal sructure. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered. In this paper, we propose the Spatio-Temporal Curve Network (STC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Spatio-Temporal Curve (STC) module; and 2) Dilated Kernels for Graph Convolution (DK-GC). The STC module dynamically adjusts the receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections, providing an adaptive spatio-temporal coverage. In addition, we propose DK-GC to consider long-range dependencies, which results in a large receptive field without any additional parameters by applying an extended kernel to the given adjacency matrices of the graph. Our STC-Net combines these two modules and achieves state-of-the-art performance on four skeleton-based action recognition benchmarks.

Suhwan Cho, Minhyeok Lee, Seunghoon Lee et al.

Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion between different frames. This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames. IMA densely integrates context information from different modalities based on a mutual refinement. IFA injects global context of a video to the query frame, enabling a full utilization of useful properties from multiple frames. Experimental results on public benchmark datasets demonstrate that our proposed approach outperforms all existing methods by a substantial margin. The proposed two components are also thoroughly validated via ablative study.

Minhyeok Lee, Suhwan Cho, Dogyoon Lee et al.

Unsupervised video object segmentation aims to segment the most prominent object in a video sequence. However, the existence of complex backgrounds and multiple foreground objects make this task challenging. To address this issue, we propose a guided slot attention network to reinforce spatial structural information and obtain better foreground--background separation. The foreground and background slots, which are initialized with query guidance, are iteratively refined based on interactions with template information. Furthermore, to improve slot--template interaction and effectively fuse global and local features in the target and reference frames, K-nearest neighbors filtering and a feature aggregation transformer are introduced. The proposed model achieves state-of-the-art performance on two popular datasets. Additionally, we demonstrate the robustness of the proposed model in challenging scenes through various comparative experiments.

Minjung Kim, MyeongAh Cho, Sangyoun Lee

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks being fooled by similar appearances and same backgrounds. In this paper, we propose a Disentanglement and Switching and Aggregation Network (DSANet), which segregates the features representing identity and features based on camera characteristics, and pays more attention to ID information. We also introduce an auxiliary task that utilizes a new pair of features created through switching and aggregation to increase the network's capability for various camera scenarios. Furthermore, we devise a Target Localization Module (TLM) that extracts robust features against a change in the position of the target according to the frame flow and a Frame Weight Generation (FWG) that reflects temporal information in the final representation. Various loss functions for disentanglement learning are designed so that each component of the network can cooperate while satisfactorily performing its own role. Quantitative and qualitative results from extensive experiments demonstrate the superiority of DSANet over state-of-the-art methods on three benchmark datasets.

MyeongAh Cho, Tae-young Chun, g Taeoh Kim et al.

NIR-to-VIS face recognition is identifying faces of two different domains by extracting domain-invariant features. However, this is a challenging problem due to the two different domain characteristics, and the lack of NIR face dataset. In order to reduce domain discrepancy while using the existing face recognition models, we propose a 'Relation Module' which can simply add-on to any face recognition models. The local features extracted from face image contain information of each component of the face. Based on two different domain characteristics, to use the relationships between local features is more domain-invariant than to use it as it is. In addition to these relationships, positional information such as distance from lips to chin or eye to eye, also provides domain-invariant information. In our Relation Module, Relation Layer implicitly captures relationships, and Coordinates Layer models the positional information. Also, our proposed Triplet loss with conditional margin reduces intra-class variation in training, and resulting in additional performance improvements. Different from the general face recognition models, our add-on module does not need to pre-train with the large scale dataset. The proposed module fine-tuned only with CASIA NIR-VIS 2.0 database. With the proposed module, we achieve 14.81% rank-1 accuracy and 15.47% verification rate of 0.1% FAR improvements compare to two baseline models.

MyeongAh Cho, Tae-young Chung, Hyeongmin Lee et al.

The region proposal task is to generate a set of candidate regions that contain an object. In this task, it is most important to propose as many candidates of ground-truth as possible in a fixed number of proposals. In a typical image, however, there are too few hard negative examples compared to the vast number of easy negatives, so region proposal networks struggle to train on hard negatives. Because of this problem, networks tend to propose hard negatives as candidates, while failing to propose ground-truth candidates, which leads to poor performance. In this paper, we propose a Negative Region Proposal Network(nRPN) to improve Region Proposal Network(RPN). The nRPN learns from the RPN's false positives and provide hard negative examples to the RPN. Our proposed nRPN leads to a reduction in false positives and better RPN performance. An RPN trained with an nRPN achieves performance improvements on the PASCAL VOC 2007 dataset.

Seunghoon Lee, Suhwan Cho, Dogyoon Lee et al.

Unsupervised Video Object Segmentation (UVOS) refers to the challenging task of segmenting the prominent object in videos without manual guidance. In recent works, two approaches for UVOS have been discussed that can be divided into: appearance and appearance-motion-based methods, which have limitations respectively. Appearance-based methods do not consider the motion of the target object due to exploiting the correlation information between randomly paired frames. Appearance-motion-based methods have the limitation that the dependency on optical flow is dominant due to fusing the appearance with motion. In this paper, we propose a novel framework for UVOS that can address the aforementioned limitations of the two approaches in terms of both time and scale. Temporal Alignment Fusion aligns the saliency information of adjacent frames with the target frame to leverage the information of adjacent frames. Scale Alignment Decoder predicts the target object mask by aggregating multi-scale feature maps via continuous mapping with implicit neural representation. We present experimental results on public benchmark datasets, DAVIS 2016 and FBMS, which demonstrate the effectiveness of our method. Furthermore, we outperform the state-of-the-art methods on DAVIS 2016.

Chaewon Park, Minhyeok Lee, Suhwan Cho et al.

Image reconstruction-based anomaly detection has recently been in the spotlight because of the difficulty of constructing anomaly datasets. These approaches work by learning to model normal features without seeing abnormal samples during training and then discriminating anomalies at test time based on the reconstructive errors. However, these models have limitations in reconstructing the abnormal samples due to their indiscriminate conveyance of features. Moreover, these approaches are not explicitly optimized for distinguishable anomalies. To address these problems, we propose a two-stream decoder network (TSDN), designed to learn both normal and abnormal features. Additionally, we propose a feature normality estimator (FNE) to eliminate abnormal features and prevent high-quality reconstruction of abnormal regions. Evaluation on a standard benchmark demonstrated performance better than state-of-the-art models.

Minhyeok Lee, Suhwan Cho, Chaewon Park et al.

The camouflaged object detection (COD) task aims to identify and segment objects that blend into the background due to their similar color or texture. Despite the inherent difficulties of the task, COD has gained considerable attention in several fields, such as medicine, life-saving, and anti-military fields. In this paper, we propose a novel solution called the Deformable Point Sampling network (DPS-Net) to address the challenges associated with COD. The proposed DPS-Net utilizes a Deformable Point Sampling transformer (DPS transformer) that can effectively capture sparse local boundary information of significant object boundaries in COD using a deformable point sampling method. Moreover, the DPS transformer demonstrates robust COD performance by extracting contextual features for target object localization through integrating rough global positional information of objects with boundary local information. We evaluate our method on three prominent datasets and achieve state-of-the-art performance. Our results demonstrate the effectiveness of the proposed method through comparative experiments.

Suhwan Cho, Woo Jin Kim, MyeongAh Cho et al.

Feature similarity matching, which transfers the information of the reference frame to the query frame, is a key component in semi-supervised video object segmentation. If surjective matching is adopted, background distractors can easily occur and degrade the performance. Bijective matching mechanisms try to prevent this by restricting the amount of information being transferred to the query frame, but have two limitations: 1) surjective matching cannot be fully leveraged as it is transformed to bijective matching at test time; and 2) test-time manual tuning is required for searching the optimal hyper-parameters. To overcome these limitations while ensuring reliable information transfer, we introduce an equalized matching mechanism. To prevent the reference frame information from being overly referenced, the potential contribution to the query frame is equalized by simply applying a softmax operation along with the query. On public benchmark datasets, our proposed approach achieves a comparable performance to state-of-the-art methods.

Minhyeok Lee, Suhwan Cho, Chajin Shin et al.

Propagation-based video inpainting using optical flow at the pixel or feature level has recently garnered significant attention. However, it has limitations such as the inaccuracy of optical flow prediction and the propagation of noise over time. These issues result in non-uniform noise and time consistency problems throughout the video, which are particularly pronounced when the removed area is large and involves substantial movement. To address these issues, we propose a novel First Frame Filling Video Diffusion Inpainting model (FFF-VDI). We design FFF-VDI inspired by the capabilities of pre-trained image-to-video diffusion models that can transform the first frame image into a highly natural video. To apply this to the video inpainting task, we propagate the noise latent information of future frames to fill the masked areas of the first frame's noise latent code. Next, we fine-tune the pre-trained image-to-video diffusion model to generate the inpainted video. The proposed model addresses the limitations of existing methods that rely on optical flow quality, producing much more natural and temporally consistent videos. This proposed approach is the first to effectively integrate image-to-video diffusion models into video inpainting tasks. Through various comparative experiments, we demonstrate that the proposed model can robustly handle diverse inpainting types with high quality.

Yongwoo Lee, Minhyeok Lee, Suhwan Cho et al.

Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this use a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the structures in the image nor the relations between distant pixels, conventional methods cannot deal with complex scenes effectively. In this paper, we propose an adaptive graph convolution module (AGCM) to overcome these limitations. Prototype features are initially extracted from the input image using a learnable region generation layer that spatially groups features in the image. The prototype features are then refined by propagating information between them based on a graph architecture, where each feature is regarded as a node. Experimental results show that the proposed AGCM dramatically improves the SOD performance both quantitatively and quantitatively.

Sangjin Lee, Suhwan Cho, Sangyoun Lee

Recently, removing objects from videos and filling in the erased regions using deep video inpainting (VI) algorithms has attracted considerable attention. Usually, a video sequence and object segmentation masks for all frames are required as the input for this task. However, in real-world applications, providing segmentation masks for all frames is quite difficult and inefficient. Therefore, we deal with VI in a one-shot manner, which only takes the initial frame's object mask as its input. Although we can achieve that using naive combinations of video object segmentation (VOS) and VI methods, they are sub-optimal and generally cause critical errors. To address that, we propose a unified pipeline for one-shot video inpainting (OSVI). By jointly learning mask prediction and video completion in an end-to-end manner, the results can be optimal for the entire task instead of each separate module. Additionally, unlike the two stage methods that use the predicted masks as ground truth cues, our method is more reliable because the predicted masks can be used as the network's internal guidance. On the synthesized datasets for OSVI, our proposed method outperforms all others both quantitatively and qualitatively.

Suhwan Cho, Minhyeok Lee, Jungho Lee et al.

Unsupervised video object segmentation aims to detect the most salient object in a video without any external guidance regarding the object. Salient objects often exhibit distinctive movements compared to the background, and recent methods leverage this by combining motion cues from optical flow maps with appearance cues from RGB images. However, because optical flow maps are often closely correlated with segmentation masks, networks can become overly dependent on motion cues during training, leading to vulnerability when faced with confusing motion cues and resulting in unstable predictions. To address this challenge, we propose a novel motion-as-option network that treats motion cues as an optional component rather than a necessity. During training, we randomly input RGB images into the motion encoder instead of optical flow maps, which implicitly reduces the network's reliance on motion cues. This design ensures that the motion encoder is capable of processing both RGB images and optical flow maps, leading to two distinct predictions depending on the type of input provided. To make the most of this flexibility, we introduce an adaptive output selection algorithm that determines the optimal prediction during testing.

Dogyoon Lee, Donghyeong Kim, Jungho Lee et al.

Recent studies construct deblurred neural radiance fields~(DeRF) using dozens of blurry images, which are not practical scenarios if only a limited number of blurry images are available. This paper focuses on constructing DeRF from sparse-view for more pragmatic real-world scenarios. As observed in our experiments, establishing DeRF from sparse views proves to be a more challenging problem due to the inherent complexity arising from the simultaneous optimization of blur kernels and NeRF from sparse view. Sparse-DeRF successfully regularizes the complicated joint optimization, presenting alleviated overfitting artifacts and enhanced quality on radiance fields. The regularization consists of three key components: Surface smoothness, helps the model accurately predict the scene structure utilizing unseen and additional hidden rays derived from the blur kernel based on statistical tendencies of real-world; Modulated gradient scaling, helps the model adjust the amount of the backpropagated gradient according to the arrangements of scene objects; Perceptual distillation improves the perceptual quality by overcoming the ill-posed multi-view inconsistency of image deblurring and distilling the pre-deblurred information, compensating for the lack of clean information in blurry images. We demonstrate the effectiveness of the Sparse-DeRF with extensive quantitative and qualitative experimental results by training DeRF from 2-view, 4-view, and 6-view blurry images.

Jungho Lee, Donghyeong Kim, Dogyoon Lee et al.

3D Gaussian Splatting (3DGS) has gained significant attention for their high-quality novel view rendering, motivating research to address real-world challenges. A critical issue is the camera motion blur caused by movement during exposure, which hinders accurate 3D scene reconstruction. In this study, we propose CRiM-GS, a \textbf{C}ontinuous \textbf{Ri}gid \textbf{M}otion-aware \textbf{G}aussian \textbf{S}platting that reconstructs precise 3D scenes from motion-blurred images while maintaining real-time rendering speed. Considering the complex motion patterns inherent in real-world camera movements, we predict continuous camera trajectories using neural ordinary differential equations (ODE). To ensure accurate modeling, we employ rigid body transformations with proper regularization, preserving object shape and size. Additionally, we introduce an adaptive distortion-aware transformation to compensate for potential nonlinear distortions, such as rolling shutter effects, and unpredictable camera movements. By revisiting fundamental camera theory and leveraging advanced neural training techniques, we achieve precise modeling of continuous camera trajectories. Extensive experiments demonstrate state-of-the-art performance both quantitatively and qualitatively on benchmark datasets.

Sungmin Woo, Wonjoon Lee, Woo Jin Kim et al.

Self-supervised multi-frame monocular depth estimation relies on the geometric consistency between successive frames under the assumption of a static scene. However, the presence of moving objects in dynamic scenes introduces inevitable inconsistencies, causing misaligned multi-frame feature matching and misleading self-supervision during training. In this paper, we propose a novel framework called ProDepth, which effectively addresses the mismatch problem caused by dynamic objects using a probabilistic approach. We initially deduce the uncertainty associated with static scene assumption by adopting an auxiliary decoder. This decoder analyzes inconsistencies embedded in the cost volume, inferring the probability of areas being dynamic. We then directly rectify the erroneous cost volume for dynamic areas through a Probabilistic Cost Volume Modulation (PCVM) module. Specifically, we derive probability distributions of depth candidates from both single-frame and multi-frame cues, modulating the cost volume by adaptively fusing those distributions based on the inferred uncertainty. Additionally, we present a self-supervision loss reweighting strategy that not only masks out incorrect supervision with high uncertainty but also mitigates the risks in remaining possible dynamic areas in accordance with the probability. Our proposed method excels over state-of-the-art approaches in all metrics on both Cityscapes and KITTI datasets, and demonstrates superior generalization ability on the Waymo Open dataset.

Suhwan Cho, Minhyeok Lee, Jungho Lee et al.

Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-stream approaches that leverage both RGB images and optical flow maps have gained significant attention. However, the limited amount of training data remains a substantial challenge. In this study, we propose a novel data generation method that simulates fake optical flows from single images, thereby creating large-scale training data for stable network learning. Inspired by the observation that optical flow maps are highly dependent on depth maps, we generate fake optical flows by refining and augmenting the estimated depth maps of each image. By incorporating our simulated image-flow pairs, we achieve new state-of-the-art performance on all public benchmark datasets without relying on complex modules. We believe that our data generation method represents a potential breakthrough for future VOS research.

Inseok Jeon, Suhwan Cho, Minhyeok Lee et al.

Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues. Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation through relation transformer blocks. To improve learning efficiency, we incorporate a token masking strategy that addresses the limitations of relying solely on increased model complexity. Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods.

Inseok Jeon, Minhyeok Lee, Seunghoon Lee et al.

Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial context. These limitations lead to intraframe and inter-frame inconsistencies, which become particularly pronounced in dynamic scenes and large outpainting scenarios. To overcome these challenges, we propose Seen-to-Scene, a novel framework that unifies propagationbased and generation-based paradigms for video outpainting. Specifically, Seen-to-Scene leverages flow-based propagation with a flow completion network pre-trained for video inpainting, which is fine-tuned in an end-to-end manner to bridge the domain gap and reconstruct coherent motion fields. To further improve the efficiency and reliability of propagation, we introduce a reference-guided latent propagation that effectively propagates source content across frames. Extensive experiments demonstrate that our method achieves superior temporal coherence and visual realism with efficient inference, surpassing even prior state-of-the-art methods that require input-specific adaptation.

Minseok Kang, Minhyeok Lee, Minjung Kim et al.

Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse temporal labeling, significantly reducing annotation costs. Without ground-truth bounding boxes, these methods rely on off-the-shelf detectors to generate object proposals, yet largely overlook a fundamental discrepancy from fullysupervised pipelines. Fully-supervised detectors implicitly filter out noninteractive objects, while off-the-shelf detectors indiscriminately detect all visible objects, overwhelming relation models with noisy pairs.We address this by introducing a learnable pair affinity that estimates the likelihood of interaction between subject-object pairs. Through Pair Affinity Learning and Scoring (PALS), pair affinity is incorporated into inferencetime ranking and further integrated into contextual reasoning through Pair Affinity Modulation (PAM), enabling the model to suppress noninteractive pairs and focus on relationally meaningful ones. To provide cleaner supervision for pair affinity learning, we further propose Relation- Aware Matching (RAM), which leverages vision-language grounding to resolve class-level ambiguity in pseudo-label generation. Extensive experiments on Action Genome demonstrate that our approach consistently yields substantial improvements across different baselines and backbones, achieving state-of-the-art WS-VSGG performance.

Sunghun Yang, Minhyeok Lee, Jungho Lee et al.

Monocular 3D object detection offers a cost-effective solution for autonomous driving but suffers from ill-posed depth and limited field of view. These constraints cause a lack of geometric cues and reduced accuracy in occluded or truncated scenes. While recent approaches incorporate additional depth information to address geometric ambiguity, they overlook the visual cues crucial for robust recognition. We propose MonoCLUE, which enhances monocular 3D detection by leveraging both local clustering and generalized scene memory of visual features. First, we perform K-means clustering on visual features to capture distinct object-level appearance parts (e.g., bonnet, car roof), improving detection of partially visible objects. The clustered features are propagated across regions to capture objects with similar appearances. Second, we construct a generalized scene memory by aggregating clustered features across images, providing consistent representations that generalize across scenes. This improves object-level feature consistency, enabling stable detection across varying environments. Lastly, we integrate both local cluster features and generalized scene memory into object queries, guiding attention toward informative regions. Exploiting a unified local clustering and generalized scene memory strategy, MonoCLUE enables robust monocular 3D detection under occlusion and limited visibility, achieving state-of-the-art performance on the KITTI benchmark.

Minhyeok Lee, Dogyoon Lee, Jungho Lee et al.

Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model multimodal features from pretrained encoders and effectively fusing them using transformer-based cross-modal attention. While these methods match language features with image features to effectively identify likely target objects, they often struggle to correctly understand contextual information in complex and ambiguous sentences and scenes. To address this issue, we propose a novel bidirectional token-masking autoencoder (BTMAE) inspired by the masked autoencoder (MAE). The proposed model learns the context of image-to-language and language-to-image by reconstructing missing features in both image and language features at the token level. In other words, this approach involves mutually complementing across the features of images and language, with a focus on enabling the network to understand interconnected deep contextual information between the two modalities. This learning method enhances the robustness of RIS performance in complex sentences and scenes. Our BTMAE achieves state-of-the-art performance on three popular datasets, and we demonstrate the effectiveness of the proposed method through various ablation studies.

Wonjoon Lee, Sungmin Woo, Donghyeong Kim et al.

Online reconstruction of dynamic scenes aims to learn from streaming multi-view inputs under low-latency constraints. The fast training and real-time rendering capabilities of 3D Gaussian Splatting have made on-the-fly reconstruction practically feasible, enabling online 4D reconstruction. However, existing online approaches, despite their efficiency and visual quality, fail to learn per-Gaussian motion that reflects true scene dynamics. Without explicit motion cues, appearance and motion are optimized solely under photometric loss, causing per-Gaussian motion to chase pixel residuals rather than true 3D motion. To address this, we propose MoRGS, an efficient online per-Gaussian motion reasoning framework that explicitly models per-Gaussian motion to improve 4D reconstruction quality. Specifically, we leverage optical flow on a sparse set of key views as lightweight motion cues that regularize per-Gaussian motion beyond photometric supervision. To compensate for the sparsity of flow supervision, we learn a per-Gaussian motion offset field that reconciles discrepancies between projected 3D motion and observed flow across views and time. In addition, we introduce a per-Gaussian motion confidence that separates dynamic from static Gaussians and weights Gaussian attribute residual updates, thereby suppressing redundant motion in static regions for better temporal consistency and accelerating the modeling of large motions. Extensive experiments demonstrate that MoRGS achieves state-of-the-art reconstruction quality and motion fidelity among online methods, while maintaining streamable performance.

Sangyoun Lee, Juho Jung, Changdae Oh et al.

Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformers have limitations in capturing long-range dependencies and temporal causality. To address these challenges, we propose a novel TAL architecture leveraging the Selective State Space Model (S6). Our approach integrates the Feature Aggregated Bi-S6 block, Dual Bi-S6 structure, and a recurrent mechanism to enhance temporal and channel-wise dependency modeling without increasing parameter complexity. Extensive experiments on benchmark datasets demonstrate state-of-the-art results with mAP scores of 74.2% on THUMOS-14, 42.9% on ActivityNet, 29.6% on FineAction, and 45.8% on HACS. Ablation studies validate our method's effectiveness, showing that the Dual structure in the Stem module and the recurrent mechanism outperform traditional approaches. Our findings demonstrate the potential of S6-based models in TAL tasks, paving the way for future research.

Minseok Kang, Minhyeok Lee, Jungho Lee et al.

As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across frames. Training-free token compression has emerged as a practical solution to this bottleneck. However, existing temporal compression methods rely primarily on cross-frame token similarity or segmentation heuristics, overlooking each token's semantic role within its frame and failing to adapt compression strength to the compressibility of each frame pair. In this work, we propose OTT-Vid, a transport-derived allocation framework for temporal token compression. Our approach consists of two stages: spatial pruning identifies representative content within each frame, and optimal transport (OT) is then solved between neighboring frames to estimate temporal compressibility. We formulate this OT with non-uniform token mass, which protects semantically important tokens from aggressive compression, and a locality-aware cost that captures both feature and spatial disparities. The resulting transport plan jointly balances token importance and matching cost, while its total cost defines the transport difficulty of each frame pair, which we use to allocate compression budgets dynamically. Experiments on six benchmarks spanning video question answering and temporal grounding show that OTT-Vid preserves 95.8% of VQA and 73.9% of VTG performance while retaining only 10% of tokens, consistently outperforming existing state-of-the-art training-free compression methods.

Taeoh Kim, Hyeongmin Lee, MyeongAh Cho et al.

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor in improving recognition performance and robustness. Data augmentation based on visual inductive priors, such as cropping, flipping, rotating, or photometric jittering, is a representative approach to achieve these features. Recent state-of-the-art recognition solutions have relied on modern data augmentation strategies that exploit a mixture of augmentation operations. In this study, we extend these strategies to the temporal dimension for videos to learn temporally invariant or temporally localizable features to cover temporal perturbations or complex actions in videos. Based on our novel temporal data augmentation algorithms, video recognition performances are improved using only a limited amount of training data compared to the spatial-only data augmentation algorithms, including the 1st Visual Inductive Priors (VIPriors) for data-efficient action recognition challenge. Furthermore, learned features are temporally localizable that cannot be achieved using spatial augmentation algorithms. Our source code is available at https://github.com/taeoh-kim/temporal_data_augmentation.

Chajin Shin, Sangjin Lee, Sangyoun Lee

Recently, significant improvements in rate-distortion performance of image compression have been achieved with deep-learning techniques. A key factor in this success is the use of additional bits to predict an approximation of the latent vector, which is the output of the encoder, through another neural network. Then, only the difference between the prediction and the latent vector is coded into the bitstream, along with its estimated probability distribution. We introduce a new predictive structure consisting of the auxiliary coarse network and the main network, inspired by neural video compression. The auxiliary coarse network encodes the auxiliary information and predicts the approximation of the original image as multi-scale features. The main network encodes the residual between the predicted feature from the auxiliary coarse network and the feature of the original image. To further leverage our new structure, we propose Auxiliary info-guided Feature Prediction (AFP) module that uses global correlation to predict more accurate predicted features. Moreover, we present Context Junction module that refines the auxiliary feature from AFP module and produces the residuals between the refined features and the original image features. Finally, we introduce Auxiliary info-guided Parameter Estimation (APE) module, which predicts the approximation of the latent vector and estimates the probability distribution of these residuals. We demonstrate the effectiveness of the proposed modules by various ablation studies. Under extensive experiments, our model outperforms other neural image compression models and achieves a 19.49\% higher rate-distortion performance than VVC on Tecnick dataset.

Juho Jung, Sangyoun Lee, Jooeon Kang et al.

All current benchmarks for multimodal deepfake detection manipulate entire frames using various generation techniques, resulting in oversaturated detection accuracies exceeding 94% at the video-level classification. However, these benchmarks struggle to detect dynamic deepfake attacks with challenging frame-by-frame alterations presented in real-world scenarios. To address this limitation, we introduce FakeMix, a novel clip-level evaluation benchmark aimed at identifying manipulated segments within both video and audio, providing insight into the origins of deepfakes. Furthermore, we propose novel evaluation metrics, Temporal Accuracy (TA) and Frame-wise Discrimination Metric (FDM), to assess the robustness of deepfake detection models. Evaluating state-of-the-art models against diverse deepfake benchmarks, particularly FakeMix, demonstrates the effectiveness of our approach comprehensively. Specifically, while achieving an Average Precision (AP) of 94.2% at the video-level, the evaluation of the existing models at the clip-level using the proposed metrics, TA and FDM, yielded sharp declines in accuracy to 53.1%, and 52.1%, respectively.

Jungho Lee, Dogyoon Lee, Minhyeok Lee et al.

Neural radiance fields (NeRF) has attracted considerable attention for their exceptional ability in synthesizing novel views with high fidelity. However, the presence of motion blur, resulting from slight camera movements during extended shutter exposures, poses a significant challenge, potentially compromising the quality of the reconstructed 3D scenes. To effectively handle this issue, we propose sequential motion understanding radiance fields (SMURF), a novel approach that models continuous camera motion and leverages the explicit volumetric representation method for robustness to motion-blurred input images. The core idea of the SMURF is continuous motion blurring kernel (CMBK), a module designed to model a continuous camera movements for processing blurry inputs. Our model is evaluated against benchmark datasets and demonstrates state-of-the-art performance both quantitatively and qualitatively.

Sungmin Woo, Minjung Kim, Donghyeong Kim et al.

Multi-agent motion prediction is a crucial concern in autonomous driving, yet it remains a challenge owing to the ambiguous intentions of dynamic agents and their intricate interactions. Existing studies have attempted to capture interactions between road entities by using the definite data in history timesteps, as future information is not available and involves high uncertainty. However, without sufficient guidance for capturing future states of interacting agents, they frequently produce unrealistic trajectory overlaps. In this work, we propose Future Interaction modeling for Motion Prediction (FIMP), which captures potential future interactions in an end-to-end manner. FIMP adopts a future decoder that implicitly extracts the potential future information in an intermediate feature-level, and identifies the interacting entity pairs through future affinity learning and top-k filtering strategy. Experiments show that our future interaction modeling improves the performance remarkably, leading to superior performance on the Argoverse motion forecasting benchmark.

Minhyeok Lee, Suhwan Cho, Jungho Lee et al.

Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment Anything Model (SAM), with a pre-trained vision-language model like CLIP. But these two-stage approaches often suffer from high computational costs, memory inefficiencies. In this paper, we propose ESC-Net, a novel one-stage open-vocabulary segmentation model that leverages the SAM decoder blocks for class-agnostic segmentation within an efficient inference framework. By embedding pseudo prompts generated from image-text correlations into SAM's promptable segmentation framework, ESC-Net achieves refined spatial aggregation for accurate mask predictions. ESC-Net achieves superior performance on standard benchmarks, including ADE20K, PASCAL-VOC, and PASCAL-Context, outperforming prior methods in both efficiency and accuracy. Comprehensive ablation studies further demonstrate its robustness across challenging conditions.

Suhwan Cho, Seunghoon Lee, Minhyeok Lee et al.

Referring video object segmentation aims to segment and track a target object in a video using a natural language prompt. Existing methods typically fuse visual and textual features in a highly entangled manner, processing multi-modal information together to generate per-frame masks. However, this approach often struggles with ambiguous target identification, particularly in scenes with multiple similar objects, and fails to ensure consistent mask propagation across frames. To address these limitations, we introduce FindTrack, an efficient decoupled framework that separates target identification from mask propagation. FindTrack first adaptively selects a key frame by balancing segmentation confidence and vision-text alignment, establishing a robust reference for the target object. This reference is then utilized by a dedicated propagation module to track and segment the object across the entire video. By decoupling these processes, FindTrack effectively reduces ambiguities in target association and enhances segmentation consistency. FindTrack significantly outperforms all existing methods on public benchmarks, demonstrating its superiority.

Suhwan Cho, Seoung Wug Oh, Sangyoun Lee et al.

Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video. In this study, we propose a robust and practical VI framework that leverages a large generative model for reference generation in combination with an advanced pixel propagation algorithm. Powered by a strong generative model, our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts. For pixel propagation, we introduce a one-shot pixel pulling method that effectively avoids error accumulation from repeated sampling while maintaining sub-pixel precision. To evaluate various VI methods in realistic scenarios, we also propose a high-quality VI benchmark, HQVI, comprising carefully generated videos using alpha matte composition. On public benchmarks and the HQVI dataset, our method demonstrates significantly higher visual quality and metric scores compared to existing solutions. Furthermore, it can process high-resolution videos exceeding 2K resolution with ease, underscoring its superiority for real-world applications.

Donghyeong Kim, Chaewon Park, Suhwan Cho et al.

Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen categories by leveraging CLIP's zero-shot capabilities to match text prompts with visual features. A key challenge in ZSAD is learning general prompts stably and utilizing them effectively, while maintaining both generalizability and category specificity. Although general prompts have been explored in prior works, achieving their stable optimization and effective deployment remains a significant challenge. In this work, we propose GenCLIP, a novel framework that learns and leverages general prompts more effectively through multi-layer prompting and dual-branch inference. Multi-layer prompting integrates category-specific visual cues from different CLIP layers, enriching general prompts with more comprehensive and robust feature representations. By combining general prompts with multi-layer visual features, our method further enhances its generalization capability. To balance specificity and generalization, we introduce a dual-branch inference strategy, where a vision-enhanced branch captures fine-grained category-specific features, while a query-only branch prioritizes generalization. The complementary outputs from both branches improve the stability and reliability of anomaly detection across unseen categories. Additionally, we propose an adaptive text prompt filtering mechanism, which removes irrelevant or atypical class names not encountered during CLIP's training, ensuring that only meaningful textual inputs contribute to the final vision-language alignment.

Jungho Lee, Suhwan Cho, Taeoh Kim et al.

3D Gaussian Splatting (3DGS) has attracted significant attention for its high-quality novel view rendering, inspiring research to address real-world challenges. While conventional methods depend on sharp images for accurate scene reconstruction, real-world scenarios are often affected by defocus blur due to finite depth of field, making it essential to account for realistic 3D scene representation. In this study, we propose CoCoGaussian, a Circle of Confusion-aware Gaussian Splatting that enables precise 3D scene representation using only defocused images. CoCoGaussian addresses the challenge of defocus blur by modeling the Circle of Confusion (CoC) through a physically grounded approach based on the principles of photographic defocus. Exploiting 3D Gaussians, we compute the CoC diameter from depth and learnable aperture information, generating multiple Gaussians to precisely capture the CoC shape. Furthermore, we introduce a learnable scaling factor to enhance robustness and provide more flexibility in handling unreliable depth in scenes with reflective or refractive surfaces. Experiments on both synthetic and real-world datasets demonstrate that CoCoGaussian achieves state-of-the-art performance across multiple benchmarks.

Sunghun Yang, Minhyeok Lee, Suhwan Cho et al.

Video monocular depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocular depth estimation models perform well on single images but struggle with depth consistency across video frames. Traditional methods aim to improve temporal consistency using multi-frame temporal modules or prior information like optical flow and camera parameters. However, these approaches face issues such as high memory use, reduced performance with dynamic or irregular motion, and limited motion understanding. We propose STATIC, a novel model that independently learns temporal consistency in static and dynamic area without additional information. A difference mask from surface normals identifies static and dynamic area by measuring directional variance. For static area, the Masked Static (MS) module enhances temporal consistency by focusing on stable regions. For dynamic area, the Surface Normal Similarity (SNS) module aligns areas and enhances temporal consistency by measuring feature similarity between frames. A final refinement integrates the independently learned static and dynamic area, enabling STATIC to achieve temporal consistency across the entire sequence. Our method achieves state-of-the-art video depth estimation on the KITTI and NYUv2 datasets without additional information.

Jungho Lee, Minhyeok Lee, Sunghun Yang et al.

3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches.

Minseok Kang, Minhyeok Lee, Minjung Kim et al.

Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). While recent advances have been progressed by powerful pretrained vision-language models such as CLIP and InternVideo2, existing approaches commonly treat all text tokens uniformly during crossmodal attention, disregarding their distinct semantic roles. To validate the limitations of this approach, we conduct controlled experiments demonstrating that VTG models overly rely on [EOS]-driven global semantics while failing to effectively utilize word-level signals, which limits their ability to achieve fine-grained temporal alignment. Motivated by this limitation, we propose DualGround, a dual-branch architecture that explicitly separates global and local semantics by routing the [EOS] token through a sentence-level path and clustering word tokens into phrase-level units for localized grounding. Our method introduces (1) tokenrole- aware cross modal interaction strategies that align video features with sentence-level and phrase-level semantics in a structurally disentangled manner, and (2) a joint modeling framework that not only improves global sentence-level alignment but also enhances finegrained temporal grounding by leveraging structured phrase-aware context. This design allows the model to capture both coarse and localized semantics, enabling more expressive and context-aware video grounding. DualGround achieves state-of-the-art performance on both Moment Retrieval and Highlight Detection tasks across QVHighlights and Charades- STA benchmarks, demonstrating the effectiveness of disentangled semantic modeling in video-language alignment.

Sungmin Woo, Sangyoun Lee

Depth-from-Focus (DFF) enables precise depth estimation by analyzing focus cues across a stack of images captured at varying focal lengths. While recent learning-based approaches have advanced this field, they often struggle in complex scenes with fine textures or abrupt depth changes, where focus cues may become ambiguous or misleading. We present DualFocus, a novel DFF framework that leverages the focal stack's unique gradient patterns induced by focus variation, jointly modeling focus changes over spatial and focal dimensions. Our approach introduces a variational formulation with dual constraints tailored to DFF: spatial constraints exploit gradient pattern changes across focus levels to distinguish true depth edges from texture artifacts, while focal constraints enforce unimodal, monotonic focus probabilities aligned with physical focus behavior. These inductive biases improve robustness and accuracy in challenging regions. Comprehensive experiments on four public datasets demonstrate that DualFocus consistently outperforms state-of-the-art methods in both depth accuracy and perceptual quality.

Suhwan Cho, Minhyeok Lee, Jungho Lee et al.

Unsupervised video object segmentation (VOS) aims to detect the most prominent object in a video. Recently, two-stream approaches that leverage both RGB images and optical flow have gained significant attention, but their performance is fundamentally constrained by the scarcity of training data. To address this, we propose DepthFlow, a novel data generation method that synthesizes optical flow from single images. Our approach is driven by the key insight that VOS models depend more on structural information embedded in flow maps than on their geometric accuracy, and that this structure is highly correlated with depth. We first estimate a depth map from a source image and then convert it into a synthetic flow field that preserves essential structural cues. This process enables the transformation of large-scale image-mask pairs into image-flow-mask training pairs, dramatically expanding the data available for network training. By training a simple encoder-decoder architecture with our synthesized data, we achieve new state-of-the-art performance on all public VOS benchmarks, demonstrating a scalable and effective solution to the data scarcity problem.