检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Text2PointCloud: Text-Driven Stylization for Sparse PointCloud

Text2PointCloud: Text-Driven Stylization for Sparse PointClo...

引用

44th Annual Conference on European Association for Computer Graphics, EUROGRAPHICS 2023

作者： Hwang, Inwoo Kim, Hyeonwoo Lim, Donggeun Park, Inbum Kim, Young Min Seoul National University Department of Electrical and Computer Engineering Korea Republic of Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Korea Republic of

ISBN: (纸本)9783038682097

We present Text2PointCloud, a method to process sparse, noisy point cloud input and generate high-quality stylized output. Given point cloud data, our iterative pipeline stylizes and deforms points guided by a text description and gradually densifies the point cloud. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated 3D datasets with high-quality textures, which are produced by skillful artists or high-resolution colored 3D models. Also, since we represent 3D shapes as a point cloud, we can visualize fine-grained geometric variations with a complex topology such as flowers or fire. To the best of our knowledge, it is the first approach for directly stylizing the uncolored, sparse point cloud input without converting it into a mesh or implicit representation, which might fail to express the original information in the measurements, especially when the object exhibits complex topology. © 2023 Authors.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition

Ev-TTA: Test-Time Adaptation for Event-Based Object Recognit...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Kim, Junho Hwang, Inwoo Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition. While event cameras are proposed to provide measurements of scenes with fast motions or drastic illumination changes, many existing event-based recognition algorithms suffer from performance deterioration under extreme conditions due to significant domain shifts. Ev-TTA mitigates the severe domain gaps by fine-tuning the pre-trained classifiers during the test phase using loss functions inspired by the spatio-temporal characteristics of events. Since the event data is a temporal stream of measurements, our loss function enforces similar predictions for adjacent events to quickly adapt to the changed environment online. Also, we utilize the spatial correlations between two polarities of events to handle noise under extreme illumination, where different polarities of events exhibit distinctive noise distributions. Ev-TTA demonstrates a large amount of performance gain on a wide range of event-based object recognition tasks without extensive additional training. Our formulation can be successfully applied regardless of input representations and further extended into regression tasks. We expect Ev-TTA to provide the key technique to deploy event-based vision algorithms in challenging real-world applications where significant domain shift is inevitable.

关键词： Training Lighting Performance gain Prediction algorithms Cameras Loss measurement Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

Text2Scene: Text-driven Indoor Scene Stylization with Part-a...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hwang, Inwoo Kim, Hyeonwoo Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (纸本)9798350301298

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects.

关键词： Computational imaging

来源：评论

学校读者我要写书评

暂无评论

Calibrating Panoramic Depth Estimation for Practical Localization and Mapping

Calibrating Panoramic Depth Estimation for Practical Localiz...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Kim, Junho Lee, Eun Sun Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (纸本)9798350307184

The absolute depth values of surrounding environments provide crucial cues for various assistive technologies, such as localization, navigation, and 3D structure estimation. We propose that accurate depth estimated from panoramic images can serve as a powerful and light-weight input for a wide range of downstream tasks requiring 3D information. While panoramic images can easily capture the surrounding context from commodity devices, the estimated depth shares the limitations of conventional image-based depth estimation;the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations. By taking advantage of the holistic view, we mitigate such effects in a self-supervised way and fine-tune the network with geometric consistency during the test phase. Specifically, we construct a 3D point cloud from the current depth prediction and project the point cloud at various viewpoints or apply stretches on the current input image to generate synthetic panoramas. Then we minimize the discrepancy of the 3D structure estimated from synthetic images without collecting additional data. We empirically evaluate our method in robot navigation and map-free localization where our method shows large performance enhancements. Our calibration method can therefore widen the applicability under various external conditions, serving as a key component for practical panorama-based machine vision systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ev-NeRF: Event Based Neural Radiance Field 23

Ev-NeRF: Event Based Neural Radiance Field

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Hwang, Inwoo Kim, Junho Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (纸本)9781665493468

We present Ev-NeRF, a Neural Radiance Field derived from event data. While event cameras can measure subtle brightness changes in high frame rates, the measurements in low lighting or extreme motion suffer from significant domain discrepancy with complex noise. As a result, the performance of event-based vision tasks does not transfer to challenging environments, where the event cameras are expected to thrive over normal cameras. We find that the multi-view consistency of NeRF provides a powerful self-supervision signal for eliminating spurious measurements and extracting the consistent underlying structure despite highly noisy input. Instead of posed images of the original NeRF, the input to Ev-NeRF is the event measurements accompanied by the movements of the sensors. Using the loss function that reflects the measurement model of the sensor, Ev-NeRF creates an integrated neural volume that summarizes the unstructured and sparse data points captured for about 2-4 seconds. The generated neural volume can also produce intensity images from novel views with reasonable depth estimates, which can serve as a high-quality input to various vision-based tasks. Our results show that Ev-NeRF achieves competitive performance for intensity image reconstruction under extreme noise and high-dynamic-range imaging.

关键词： Image sensors Solid modeling Volume measurement Lighting Cameras Loss measurement Sensors

来源：评论

学校读者我要写书评

暂无评论

CPO: Change Robust Panorama to Point Cloud Localization 1

引用

17th European Conference on Computer Vision (ECCV)

作者： Kim, Junho Jang, Hojun Choi, Changwoon Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (数字)9783031200779

ISBN: (纸本)9783031200762;9783031200779

We present CPO, a fast and robust algorithm that localizes a 2D panorama with respect to a 3D point cloud of a scene possibly containing changes. To robustly handle scene changes, our approach deviates from conventional feature point matching, and focuses on the spatial context provided from panorama images. Specifically, we propose efficient color histogram generation and subsequent robust localization using score maps. By utilizing the unique equivariance of spherical projections, we propose very fast color histogram generation for a large number of camera poses without explicitly rendering images for all candidate poses. We accumulate the regional consistency of the panorama and point cloud as 2D/3D score maps, and use them to weigh the input color values to further increase robustness. The weighted color distribution quickly finds good initial poses and achieves stable convergence for gradient-based optimization. CPO is lightweight and achieves effective localization in all tested scenarios, showing stable performance despite scene changes, repetitive structures, or featureless regions, which are typical challenges for visual localization with perspective cameras.

关键词： Visual localization Panorama Point cloud

来源：评论

学校读者我要写书评

暂无评论

LDL: Line Distance Functions for Panoramic Localization

LDL: Line Distance Functions for Panoramic Localization

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Kim, Junho Choi, Changwoon Jang, Hojun Kim, Young Min Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ INMC Seoul South Korea

ISBN: (纸本)9798350307184

We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments. LDL focuses on the sparse structural information of lines in the scene, which is robust to illumination changes and can potentially enable efficient computation. While previous line-based localization approaches tend to sacrifice accuracy or computation time, our method effectively observes the holistic distribution of lines within panoramic images and 3D maps. Specifically, LDL matches the distribution of lines with 2D and 3D line distance functions, which are further decomposed along principal directions of lines to increase the expressiveness. The distance functions provide coarse pose estimates by comparing the distributional information, where the poses are further optimized using conventional local feature matching. As our pipeline solely leverages line geometry and local features, it does not require costly additional training of line-specific features or correspondence matching. Nevertheless, our method demonstrates robust performance on challenging scenarios including object layout changes, illumination shifts, and large-scale scenes, while exhibiting fast pose search terminating within a matter of milliseconds. We thus expect our method to serve as a practical solution for line-based localization, and complement the well-established point-based paradigm. The code for LDL is available through the following link: https://github. com/82magnolia/ panoramic-localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Stego: Training-free diffusion generative steganography via message projection

引用

Information Sciences 2025年 718卷

作者： Daegyu Kim Chaehun Shin Jooyoung Choi Dahuin Jung Sungroh Yoon Data Science and AI Laboratory Electrical and Computer Engineering Seoul National University Seoul 08826 Republic of Korea School of Computer Science and Engineering Soongsil University Seoul 06978 Republic of Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul 08826 Republic of Korea AIIS ASRI INMC and ISRC Seoul National University Seoul 08826 Republic of Korea

Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection ability over cover images. However, they create relatively unrealistic stego images because of the inherent limitations of generative models. We propose Diffusion-Stego, a generative steganography approach based on diffusion models that outperform other generative models in image generation. Diffusion-Stego projects secret messages into the latent noise of diffusion models and generates stego images with an iterative denoising process. Since the naive hiding of secret messages into noise boosts visual degradation and decreases extracted message accuracy, we introduce message projection, which hides messages into noise space while addressing these issues. We suggest three options for message projection to adjust the trade-off between extracted message accuracy, anti-detection ability, and image quality. Diffusion-Stego is a training-free approach, so we can apply it to pre-trained diffusion models that generate high-quality images, or even large-scale text-to-image models, such as Stable diffusion. Diffusion-Stego achieved a high capacity of messages as well as high quality that makes it challenging to distinguish from real images in the PNG format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PRIORGRAD: IMPROVING CONDITIONAL DENOISING DIFFUSION MODELS WITH DATA-DEPENDENT ADAPTIVE PRIOR 10

PRIORGRAD: IMPROVING CONDITIONAL DENOISING DIFFUSION MODELS ...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Lee, Sang-Gil Kim, Heeseung Shin, Chaehun Tan, Xu Liu, Chang Meng, Qi Qin, Tao Chen, Wei Yoon, Sungroh Liu, Tie-Yan Data Science & AI Lab. Seoul National University Korea Republic of Microsoft Research Asia AIIS ASRI INMC ISRC NSI Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the corresponding data distribution may be more complicated than the standard Gaussian distribution, which potentially introduces inefficiency in denoising the prior noise into the data sample because of the discrepancy between the data and the prior. In this paper, we propose PriorGrad to improve the efficiency of the conditional diffusion model for speech synthesis (for example, a vocoder using a mel-spectrogram as the condition) by applying an adaptive prior derived from the data statistics based on the conditional information. We formulate the training and sampling procedures of PriorGrad and demonstrate the advantages of an adaptive prior through a theoretical analysis. Focusing on the speech synthesis domain, we consider the recently proposed diffusion-based speech generative models based on both the spectral and time domains and show that PriorGrad achieves faster convergence and inference with superior performance, leading to an improved perceptual quality and robustness to a smaller network capacity, and thereby demonstrating the efficiency of a data-dependent adaptive prior. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：