Search

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., Comment: AAAI 2025

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.

In many video processing tasks, leveraging large-scale image datasets is a common strategy, as image data is more abundant and facilitates comprehensive knowledge transfer. A typical approach for simulating video from static images involves applying spatial transformations, such as affine transformations and spline warping, to create sequences that mimic temporal progression. However, in tasks like video salient object detection, where both appearance and motion cues are critical, these basic image-to-video techniques fail to produce realistic optical flows that capture the independent motion properties of each object. In this study, we show that image-to-video diffusion models can generate realistic transformations of static images while understanding the contextual relationships between image components. This ability allows the model to generate plausible optical flows, preserving semantic integrity while reflecting the independent motion of scene elements. By augmenting individual images in this way, we create large-scale image-flow pairs that significantly enhance model training. Our approach achieves state-of-the-art performance across all public benchmark datasets, outperforming existing approaches.

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.

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.

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.

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., Comment: 4 pages, 2 figures, 2 tables, Accepted as Oral Presentation at The Trustworthy AI Workshop @ IJCAI 2024

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., Comment: 8 pages, 3 figures, Preprint

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.

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., Comment: Accepted by ECCV 2024. Project Page: https://sungmin-woo.github.io/prodepth/

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-filtered 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., Comment: Project page: https://dogyoonlee.github.io/sparsederf/

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., Comment: Project Page : https://jho-yonsei.github.io/CRiM-Gaussian/

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage of the network. Instead, we propose a more intuitive strategy that separates features earlier by expanding the feature sequence to the number of speakers as an extra dimension. To achieve this, an asymmetric strategy is presented in which the encoder and decoder are partitioned to perform distinct processing in separation tasks. The encoder analyzes features, and the output of the encoder is split into the number of speakers to be separated. The separated sequences are then reconstructed by the weight-shared decoder, which also performs cross-speaker processing. Without relying on speaker information, the weight-shared network in the decoder directly learns to discriminate features using a separation objective. In addition, to improve performance, traditional methods have extended the sequence length, leading to the adoption of dual-path models, which handle the much longer sequence effectively by segmenting it into chunks. To address this, we introduce global and local Transformer blocks that can directly handle long sequences more efficiently without chunking and dual-path processing. The experimental results demonstrated that this asymmetric structure is effective and that the combination of proposed global and local Transformer can sufficiently replace the role of inter- and intra-chunk processing in dual-path structure. Finally, the presented model combining both of these achieved state-of-the-art performance with much less computation in various benchmark datasets., Comment: Accepted to NeurIPS 2024; Project Page: https://dmlguq456.github.io/SepReformer_Demo

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. While recent studies have addressed this issue, they do not consider the continuous dynamics of camera movements during image acquisition, leading to inaccurate scene reconstruction. Additionally, these methods are plagued by slow training and rendering speed. To effectively handle these issues, we propose sequential motion understanding radiance fields (SMURF), a novel approach that employs neural ordinary differential equation (Neural-ODE) to model continuous camera motion and leverages the explicit volumetric representation method for faster training and robustness to motion-blurred input images. The core idea of the SMURF is continuous motion blurring kernel (CMBK), a unique module designed to model a continuous camera movements for processing blurry inputs. Our model, rigorously evaluated against benchmark datasets, demonstrates state-of-the-art performance both quantitatively and qualitatively., Comment: 25 pages, 10 figures, Code is available at https://github.com/Jho-Yonsei/SMURF

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., Comment: Accepted by ICRA 2024

Unsupervised video object segmentation (VOS) is a task that aims to detect the most salient object in a video without external guidance about the object. To leverage the property that salient objects usually have distinctive movements compared to the background, recent methods collaboratively use motion cues extracted from optical flow maps with appearance cues extracted from RGB images. However, as optical flow maps are usually very relevant to segmentation masks, the network is easy to be learned overly dependent on the motion cues during network training. As a result, such two-stream approaches are vulnerable to confusing motion cues, making their prediction unstable. To relieve this issue, we design a novel motion-as-option network by treating motion cues as optional. During network training, RGB images are randomly provided to the motion encoder instead of optical flow maps, to implicitly reduce motion dependency of the network. As the learned motion encoder can deal with both RGB images and optical flow maps, two different predictions can be generated depending on which source information is used as motion input. In order to fully exploit this property, we also propose an adaptive output selection algorithm to adopt optimal prediction result at test time. Our proposed approach affords state-of-the-art performance on all public benchmark datasets, even maintaining real-time inference speed.

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., Comment: 4 pages, 3 figures

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., Comment: Accepted to CVPR 2024

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., Comment: Accepted to ICIP 2023

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., Comment: AAAI2023 submitted

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., Comment: Accepted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023

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., Comment: WACV 2023

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., Comment: Accepted by ICCV 2023

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., Comment: ICASSP 2022

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.

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., Comment: Accepted at CVPR 2023, Code: https://github.com/dogyoonlee/DP-NeRF, Project page: https://dogyoonlee.github.io/dpnerf/

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., Comment: CVPR 2024

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, Comment: Accepted to 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (2023 ICASSP)

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., Comment: Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023

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.

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., Comment: WACV 2023

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., Comment: Accepted by ICCV 2023

Recently, learning-based image compression methods that utilize convolutional neural layers have been developed rapidly. Rescaling modules such as batch normalization which are often used in convolutional neural networks do not operate adaptively for the various inputs. Therefore, Generalized Divisible Normalization(GDN) has been widely used in image compression to rescale the input features adaptively across both spatial and channel axes. However, the representation power or degree of freedom of GDN is severely limited. Additionally, GDN cannot consider the spatial correlation of an image. To handle the limitations of GDN, we construct an expanded form of the adaptive scaling module, named Expanded Adaptive Scaling Normalization(EASN). First, we exploit the swish function to increase the representation ability. Then, we increase the receptive field to make the adaptive rescaling module consider the spatial correlation. Furthermore, we introduce an input mapping function to give the module a higher degree of freedom. We demonstrate how our EASN works in an image compression network using the visualization results of the feature map, and we conduct extensive experiments to show that our EASN increases the rate-distortion performance remarkably, and even outperforms the VVC intra at a high bit rate., Comment: ECCV2022 Accepted

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.

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.

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., Comment: Accepted to European Conference on Computer Vision (ECCV) 2022

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., Comment: ECCV 2022

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., Comment: Technical Report

Video frame interpolation (VFI) is the task that synthesizes the intermediate frame given two consecutive frames. Most of the previous studies have focused on appropriate frame warping operations and refinement modules for the warped frames. These studies have been conducted on natural videos containing only continuous motions. However, many practical videos contain various unnatural objects with discontinuous motions such as logos, user interfaces and subtitles. We propose three techniques to make the existing deep learning-based VFI architectures robust to these elements. First is a novel data augmentation strategy called figure-text mixing (FTM) which can make the models learn discontinuous motions during training stage without any extra dataset. Second, we propose a simple but effective module that predicts a map called discontinuity map (D-map), which densely distinguishes between areas of continuous and discontinuous motions. Lastly, we propose loss functions to give supervisions of the discontinuous motion areas which can be applied along with FTM and D-map. We additionally collect a special test benchmark called Graphical Discontinuous Motion (GDM) dataset consisting of some mobile games and chatting videos. Applied to the various state-of-the-art VFI networks, our method significantly improves the interpolation qualities on the videos from not only GDM dataset, but also the existing benchmarks containing only continuous motions such as Vimeo90K, UCF101, and DAVIS., Comment: highlight at CVPR 2023 (10% of accepted papers)

Recent anomaly detection algorithms have shown powerful performance by adopting frame predicting autoencoders. However, these methods face two challenging circumstances. First, they are likely to be trained to be excessively powerful, generating even abnormal frames well, which leads to failure in detecting anomalies. Second, they are distracted by the large number of objects captured in both foreground and background. To solve these problems, we propose a novel superpixel-based video data transformation technique named Random Superpixel Erasing on Moving Objects (RandomSEMO) and Moving Object Loss (MOLoss), built on top of a simple lightweight autoencoder. RandomSEMO is applied to the moving object regions by randomly erasing their superpixels. It enforces the network to pay attention to the foreground objects and learn the normal features more effectively, rather than simply predicting the future frame. Moreover, MOLoss urges the model to focus on learning normal objects captured within RandomSEMO by amplifying the loss on the pixels near the moving objects. The experimental results show that our model outperforms state-of-the-arts on three benchmarks., Comment: 4 pages, ICIP 2022 under review

UNet-based methods have shown outstanding performance in salient object detection (SOD), but are problematic in two aspects. 1) Indiscriminately integrating the encoder feature, which contains spatial information for multiple objects, and the decoder feature, which contains global information of the salient object, is likely to convey unnecessary details of non-salient objects to the decoder, hindering saliency detection. 2) To deal with ambiguous object boundaries and generate accurate saliency maps, the model needs additional branches, such as edge reconstructions, which leads to increasing computational cost. To address the problems, we propose a context fusion decoder network (CFDN) and near edge weighted loss (NEWLoss) function. The CFDN creates an accurate saliency map by integrating global context information and thus suppressing the influence of the unnecessary spatial information. NEWLoss accelerates learning of obscure boundaries without additional modules by generating weight maps on object boundaries. Our method is evaluated on four benchmarks and achieves state-of-the-art performance. We prove the effectiveness of the proposed method through comparative experiments., Comment: 4 pages, 5 figures

Semi-supervised video object segmentation (VOS) aims to track the designated objects present in the initial frame of a video at the pixel level. To fully exploit the appearance information of an object, pixel-level feature matching is widely used in VOS. Conventional feature matching runs in a surjective manner, i.e., only the best matches from the query frame to the reference frame are considered. Each location in the query frame refers to the optimal location in the reference frame regardless of how often each reference frame location is referenced. This works well in most cases and is robust against rapid appearance variations, but may cause critical errors when the query frame contains background distractors that look similar to the target object. To mitigate this concern, we introduce a bijective matching mechanism to find the best matches from the query frame to the reference frame and vice versa. Before finding the best matches for the query frame pixels, the optimal matches for the reference frame pixels are first considered to prevent each reference frame pixel from being overly referenced. As this mechanism operates in a strict manner, i.e., pixels are connected if and only if they are the sure matches for each other, it can effectively eliminate background distractors. In addition, we propose a mask embedding module to improve the existing mask propagation method. By embedding multiple historic masks with coordinate information, it can effectively capture the position information of a target object., Comment: WACV 2022

Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function that can handle an arbitrary point in continuous space. Various approaches exhibiting high performance have been proposed, but we observe that the standard pointwise feature is represented by 1D channels and can become more informative when its representation involves additional spatial feature dimensions. In this paper, we present Multidimensional Kernel Convolution (MKConv), a novel convolution operator that learns to transform the point feature representation from a vector to a multidimensional matrix. Unlike standard point convolution, MKConv proceeds via two steps. (i) It first activates the spatial dimensions of local feature representation by exploiting multidimensional kernel weights. These spatially expanded features can represent their embedded information through spatial correlation as well as channel correlation in feature space, carrying more detailed local structure information. (ii) Then, discrete convolutions are applied to the multidimensional features which can be regarded as a grid-structured matrix. In this way, we can utilize the discrete convolutions for point cloud data without voxelization that suffers from information loss. Furthermore, we propose a spatial attention module, Multidimensional Local Attention (MLA), to provide comprehensive structure awareness within the local point set by reweighting the spatial feature dimensions. We demonstrate that MKConv has excellent applicability to point cloud processing tasks including object classification, object part segmentation, and scene semantic segmentation with superior results., Comment: Accepted by Pattern Recognition 2023

Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential. However, extreme lighting conditions and complex surface objects make it difficult to predict depth in a single image. Therefore, to generate accurate depth maps, it is important for the model to learn structural information about the scene. We propose a novel Patch-Wise EdgeConv Module (PEM) and EdgeConv Attention Module (EAM) to solve the difficulty of monocular depth estimation. The proposed modules extract structural information by learning the relationship between image patches close to each other in space using edge convolution. Our method is evaluated on two popular datasets, the NYU Depth V2 and the KITTI Eigen split, achieving state-of-the-art performance. We prove that the proposed model predicts depth robustly in challenging scenes through various comparative experiments., Comment: Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

Video anomaly detection has gained significant attention due to the increasing requirements of automatic monitoring for surveillance videos. Especially, the prediction based approach is one of the most studied methods to detect anomalies by predicting frames that include abnormal events in the test set after learning with the normal frames of the training set. However, a lot of prediction networks are computationally expensive owing to the use of pre-trained optical flow networks, or fail to detect abnormal situations because of their strong generative ability to predict even the anomalies. To address these shortcomings, we propose spatial rotation transformation (SRT) and temporal mixing transformation (TMT) to generate irregular patch cuboids within normal frame cuboids in order to enhance the learning of normal features. Additionally, the proposed patch transformation is used only during the training phase, allowing our model to detect abnormal frames at fast speed during inference. Our model is evaluated on three anomaly detection benchmarks, achieving competitive accuracy and surpassing all the previous works in terms of speed., Comment: Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

The image-based lane detection algorithm is one of the key technologies in autonomous vehicles. Modern deep learning methods achieve high performance in lane detection, but it is still difficult to accurately detect lanes in challenging situations such as congested roads and extreme lighting conditions. To be robust on these challenging situations, it is important to extract global contextual information even from limited visual cues. In this paper, we propose a simple but powerful self-attention mechanism optimized for lane detection called the Expanded Self Attention (ESA) module. Inspired by the simple geometric structure of lanes, the proposed method predicts the confidence of a lane along the vertical and horizontal directions in an image. The prediction of the confidence enables estimating occluded locations by extracting global contextual information. ESA module can be easily implemented and applied to any encoder-decoder-based model without increasing the inference time. The performance of our method is evaluated on three popular lane detection benchmarks (TuSimple, CULane and BDD100K). We achieve state-of-the-art performance in CULane and BDD100K and distinct improvement on TuSimple dataset. The experimental results show that our approach is robust to occlusion and extreme lighting conditions., Comment: Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many studies proposing various augmentation methods for image data. Actually, regularization is essential for point clouds since lack of generality is more likely to occur in point cloud due to small datasets. This paper proposes a Rigid Subset Mix (RSMix), a novel data augmentation method for point clouds that generates a virtual mixed sample by replacing part of the sample with shape-preserved subsets from another sample. RSMix preserves structural information of the point cloud sample by extracting subsets from each sample without deformation using a neighboring function. The neighboring function was carefully designed considering unique properties of point cloud, unordered structure and non-grid. Experiments verified that RSMix successfully regularized the deep neural networks with remarkable improvement for shape classification. We also analyzed various combinations of data augmentations including RSMix with single and multi-view evaluations, based on abundant ablation studies., Comment: CVPR2021 Accepted, 10 pages, 5 figures, 7 tables