检索结果-内蒙古大学图书馆

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Zhen Wang, Lingli Huang, Xiang Pan, Cihui Yang, Jiaqi Realsee Shenzhen Peoples R China Northwestern Polytech Univ Xian Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Inverse rendering of complex material such as glossy, metal and mirror material is a long-standing ill-posed problem in this area, which has not been well solved. Previous approaches cannot tackle them well due to simplified BRDF and unsuitable illumination representations. In this paper, we present PhyIR, a neural inverse rendering method with a more completed SVBRDF representation and a physics-based in-network rendering layer, which can handle complex material and incorporate physical constraints by re-rendering realistic and detailed specular reflectance. Our framework estimates geometry, material and Spatially-Coherent (SC) illumination from a single indoor panorama. Due to the lack of panoramic datasets with completed SVBRDF and full-spherical light probes, we introduce an artist-designed dataset named FutureHouse with high-quality geometry, SVBRDF and per-pixel Spatially-Varying (SV) lighting. To ensure the coherence of SV lighting, a novel SC loss is proposed. Extensive experiments on both synthetic and real-world data show that the proposed method outperforms the state-of-the-arts quantitatively and qualitatively, and is able to produce photorealistic results for a number of applications such as dynamic virtual object insertion.

关键词： Geometry Reflectivity Three-dimensional displays Lighting Metals computer architecture Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates

TemporalUV: Capturing Loose Clothing with Temporally Coheren...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Xie, You Mao, Huiqi Yao, Angela Thuerey, Nils Tech Univ Munich Dept Informat Munich Germany Natl Univ Singapore Dept Comp Sci Singapore Singapore

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose a novel approach to generate temporally coherent UV coordinates for loose clothing. Our method is not constrained by human body outlines and can capture loose garments and hair. We implemented a differentiable pipeline to learn UV mapping between a sequence of RGB inputs and textures via UV coordinates. Instead of treating the UV coordinates of each frame separately, our data generation approach connects all UV coordinates via feature matching for temporal stability. Subsequently, a generative model is trained to balance the spatial quality and temporal stability. It is driven by supervised and unsupervised losses in both UV and image spaces. Our experiments show that the trained models output high-quality UV coordinates and generalize to new poses. Once a sequence of UV coordinates has been inferred by our model, it can be used to flexibly synthesize new looks and modified visual styles. Compared to existing methods, our approach reduces the computational workload to animate new outfits by several orders of magnitude.

关键词： Hair Visualization computer vision Computational modeling Clothing Pipelines Stability analysis

来源：评论

学校读者我要写书评

暂无评论

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

SE-SSD: Self-Ensembling Single-Stage Object Detector From Po...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zheng, Wu Tang, Weiliang Jiang, Li Fu, Chi-Wing Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781665445092

We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate and efficient 3D object detection in outdoor point clouds. Our key focus is on exploiting both soft and hard targets with our formulated constraints to jointly optimize the model, without introducing extra computation in the inference. Specifically, SE-SSD contains a pair of teacher and student SSDs, in which we design an effective IoU-based matching strategy to filter soft targets from the teacher and formulate a consistency loss to align student predictions with them. Also, to maximize the distilled knowledge for ensembling the teacher, we design a new augmentation scheme to produce shape-aware augmented samples to train the student, aiming to encourage it to infer complete object shapes. Lastly, to better exploit hard targets, we design an ODIoU loss to supervise the student with constraints on the predicted box centers and orientations. Our SE-SSD attains top performance compared with all prior published works. Also, it attains top precisions for car detection in the KITTI benchmark (ranked 1st and 2nd on the BEV and 3D leaderboards1, respectively) with an ultra-high inference speed. The code is available at https://***/Vegeta2020/SE-SSD.

关键词： Training Matched filters computer vision Three-dimensional displays Shape Detectors Object detection

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-Target Tracking and Data Association in vision Networks

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1397-1397页

作者： Kamal, Ahmed T. Bappy, Jawadul H. Farrell, Jay A. Roy-Chowdhury, Amit K. Univ Calif Riverside Riverside CA 92521 USA

Distributed algorithms have recently gained immense popularity. With regards to computer vision applications, distributed multi-target tracking in a camera network is a fundamental problem. The goal is for all cameras to have accurate state estimates for all targets. Distributed estimation algorithms work by exchanging information between sensors that are communication neighbors. vision-based distributed multi-target state estimation has at least two characteristics that distinguishes it from other applications. First, cameras are directional sensors and often neighboring sensors may not be sensing the same targets, i.e., they are naive with respect to that target. Second, in the presence of clutter and multiple targets, each camera must solve a data association problem. This paper presents an information-weighted, consensus-based, distributed multi-target tracking algorithm referred to as the Multi-target Information Consensus (MTIC) algorithm that is designed to address both the naivety and the data association problems. It converges to the centralized minimum mean square error estimate. The proposed MTIC algorithm and its extensions to non-linear camera models, termed as the Extended MTIC (EMTIC), are robust to false measurements and limited resources like power, bandwidth and the realtime operational requirements. Simulation and experimental analysis are provided to support the theoretical results.

关键词： Consensus distributed tracking data association camera networks

来源：评论

学校读者我要写书评

暂无评论

PairDETR : Joint Detection and Association of Human Bodies and Faces

PairDETR : Joint Detection and Association of Human Bodies a...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Ali, Ammar Gaikov, Georgii Rybalchenko, Denis Chigorin, Alexander Laptev, Ivan Zagoruyko, Sergey MTS AI ITMO Moscow Russia MTS AI Moscow Russia VisionLabs Hyderabad Telangana India MBZUAI Abu Dhabi U Arab Emirates MTS AI Skoltech Moscow Russia

ISBN: (纸本)9798350353013;9798350353006

Image and video analysis requires not only accurate object detection but also the understanding of relationships among detected objects. Common solutions to relation modeling typically resort to stand-alone object detectors followed by non-differentiable post-processing techniques. Recently introduced detection transformers (DETR) perform end-to-end object detection based on a bipartite matching loss. Such methods, however, lack the ability to jointly detect objects and resolve object associations. In this paper, we build on the DETR approach and extend it to the joint detection of objects and their relationships by introducing an approximated bipartite matching. While our method can generalize to an arbitrary number of objects, we here focus on the modeling of object pairs and their relations. In particular, we apply our method PairDETR to the problem of detecting human bodies and faces, and associating them for the same person. Our approach not only eliminates the need for hand-designed post-processing but also achieves excellent results for body-face associations. We evaluate PairDETR on the challenging CrowdHuman and CityPersons datasets and demonstrate a large improvement over the state of the art. Our training code and pre-trained models are available at https://***/mts-ai/pairdetr

关键词： Association CityPersons computer vision CrowdHuman DETR end-to-end Object detection Transformers

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Visual Search with Backward Consistent Feature Embedding

Continual Learning for Visual Search with Backward Consisten...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wan, Timmy S. T. Chen, Jun-Cheng Wu, Tzer-Yi Chen, Chu-Song Natl Taiwan Univ Taipei Taiwan Acad Sinica Taipei Taiwan Ucfunnel Co Ltd Taipei Taiwan

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, ignoring the continual updating of the model. Besides, as the model updates, the new model must re-extract features for the entire gallery set to maintain compatible feature space, imposing a high computational cost for a large gallery set. To address the issues of long-term visual search, we introduce a continual learning (CL) approach that can handle the incrementally growing gallery set with backward embedding consistency. We enforce the losses of inter-session data coherence, neighbor-session model coherence, and intra-session discrimination to conduct a continual learner. In addition to the disjoint setup, our CL solution also tackles the situation of increasingly adding new classes for the blurry boundary without assuming all categories known in the beginning and during model update. To our knowledge, this is the first CL method both tackling the issue of backward-consistent feature embedding and allowing novel classes to occur in the new sessions. Extensive experiments on various benchmarks show the efficacy of our approach under a wide range of setups(1).

关键词： Representation learning Visualization computer vision Computational modeling Coherence Benchmark testing Data models

来源：评论

学校读者我要写书评

暂无评论

Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps

Polymorphic-GAN: Generating Aligned Samples across Multiple ...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kim, Seung Wook Kreis, Karsten Li, Daiqing Torralba, Antonio Fidler, Sanja NVIDIA Santa Clara CA 95051 USA Univ Toronto Toronto ON Canada Vector Inst Bengaluru Karnataka India MIT Cambridge MA 02139 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Modern image generative models show remarkable sample quality when trained on a single domain or class of objects. In this work, we introduce a generative adversarial network that can simultaneously generate aligned image samples from multiple related domains. We leverage the fact that a variety of object classes share common attributes, with certain geometric differences. We propose Polymorphic-GAN which learns shared features across all domains and a per-domain morph layer to morph shared features according to each domain. In contrast to previous works, our framework allows simultaneous modelling of images with highly varying geometries, such as images of human faces, painted and artistic faces, as well as multiple different animal faces. We demonstrate that our model produces aligned samples for all domains and show how it can be used for applications such as segmentation transfer and cross-domain image editing, as well as training in low-data regimes. Additionally, we apply our Polymorphic-GAN on image-to-image translation tasks and show that we can greatly surpass previous approaches in cases where the geometric differences between domains are large.

关键词： Training Geometry Image segmentation computer vision Shape Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Deep Visual Odometry with Online Adaptation

Self-Supervised Deep Visual Odometry with Online Adaptation

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Shunkai Wang, Xin Cao, Yingdian Xue, Fei Yan, Zike Zha, Hongbin Peking Univ Key Lab Machine Percept MOE Sch EECS PKU SenseTime Machine Vis Joint Lab Beijing Peoples R China

ISBN: (纸本)9781728171685

Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with scenes different from the training data, which makes them unsuitable for practical applications. In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner. The proposed method utilizes convolutional long short-term memory (convLSTM) to aggregate rich spatial-temporal information in the past. The network is able to memorize and learn from its past experience for better estimation and fast adaptation to the current frame. When running VO in the open world, in order to deal with the changing environment, we propose an online feature alignment method by aligning feature distributions at different time. Our VO network is able to seamlessly adapt to different environments. Extensive experiments on unseen outdoor scenes, virtual to real world and outdoor to indoor environments demonstrate that our method consistently outperforms state-of-the-art self-supervised VO base-lines considerably.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Im2Pencil: Controllable Pencil Illustration from Photographs 32

Im2Pencil: Controllable Pencil Illustration from Photographs

引用

32nd ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Yijun Fang, Chen Hertzmann, Aaron Shechtman, Eli Yang, Ming-Hsuan UC Merced Merced CA 95343 USA ByteDance AI Beijing Peoples R China Adobe Res San Jose CA USA Google Cloud Mountain View CA USA

ISBN: (纸本)9781728132938

We propose a high-quality photo-to-pencil translation method with fine-grained control over the drawing style. This is a challenging task due to multiple stroke types (e.g., outline and shading), structural complexity of pencil shading (e.g., hatching), and the lack of aligned training data pairs. To address these challenges, we develop a two-branch model that learns separate filters for generating sketchy outlines and tonal shading from a collection of pencil drawings. We create training data pairs by extracting clean outlines and tonal illustrations from original pencil drawings using image filtering techniques, and we manually label the drawing styles. In addition, our model creates different pencil styles (e.g., line sketchiness and shading style) in a user-controllable manner. Experimental results on different types of pencil drawings show that the proposed algorithm performs favorably against existing methods in terms of quality, diversity and user evaluations.

关键词： Image and Video Synthesis vision + Graphics

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

Cross-Domain Correlation Distillation for Unsupervised Domai...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Gao, Huan Guo, Jichang Wang, Guoli Zhang, Qian Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Horizon Robot Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixelwise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the intermediate target domain to perform the adaptation from daytime to nighttime, may fail to cope with the inherent difference between datasets caused by the camera equipment and the urban style. Faced with these two types of domain shifts, i.e., the illumination and the inherent difference of the datasets, we propose a novel domain adaptation framework via cross-domain correlation distillation, called CCDistill. The invariance of illumination or inherent difference between two images is fully explored so as to make up for the lack of labels for nighttime images. Specifically, we extract the content and style knowledge contained in features, calculate the degree of inherent or illumination difference between two images. The domain adaptation is achieved using the invariance of the same kind of difference. Extensive experiments on Dark Zurich and ACDC demonstrate that CCDistill achieves the state-of-the-art performance for nighttime semantic segmentation. Notably, our method is a one-stage domain adaptation network which can avoid affecting the inference time.

关键词： Image segmentation computer vision Correlation Shape Semantics Lighting Feature extraction

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：