检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

249 篇 会议

馆藏范围

249 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

249 篇 工学
- 249 篇 计算机科学与技术...
- 83 篇 软件工程

主题

249 篇 3d from multi-vi...
1 篇 dynamic scenes
1 篇 differentiable r...
1 篇 gaussian splatti...
1 篇 depth refinement
1 篇 occupancy foreca...
1 篇 volume rendering
1 篇 neural rendering
1 篇 novel view synth...
1 篇 occupancy predic...
1 篇 human performanc...
1 篇 compact gaussian...
1 篇 mesh
1 篇 surface reconstr...
1 篇 depth completion

机构

13 篇 zhejiang univ pe...
12 篇 chinese univ hon...
10 篇 tech univ munich...
9 篇 univ hong kong p...
8 篇 shanghai ai lab ...
7 篇 univ sci & techn...
7 篇 shanghai jiao to...
7 篇 simon fraser uni...
7 篇 zhejiang univ st...
6 篇 univ toronto on
6 篇 smartmore people...
6 篇 tsinghua univ pe...
5 篇 carnegie mellon ...
5 篇 huawei noahs ark...
5 篇 lund univ lund
4 篇 peking univ peop...
4 篇 tsinghua univ sc...
4 篇 tsinghua univ de...
4 篇 wayne state univ...
4 篇 australian natl ...

作者

7 篇 zhou xiaowei
6 篇 niessner matthia...
6 篇 jia jiaya
6 篇 peng sida
6 篇 bao hujun
5 篇 tagliasacchi and...
5 篇 guibas leonidas
5 篇 liu yu-shen
4 篇 han xiaoguang
4 篇 yao ting
4 篇 qi xiaojuan
4 篇 dai angela
4 篇 theobalt christi...
4 篇 han zhizhong
4 篇 larsson viktor
3 篇 liu yuan
3 篇 lu cewu
3 篇 pollefeys marc
3 篇 chen yukang
3 篇 kim changil

语言

249 篇 英文

检索条件"主题词=3D from Multi-view and Sensors"

共 249 条记录，以下是11-20 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Learning a depth Covariance Function

Learning a Depth Covariance Function

引用

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

作者： dexheimer, Eric davison, Andrew J. Imperial Coll London Dyson Robot Lab London England

ISBN: (纸本)9798350301298

We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment...

引用

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

作者： Jiang, Yifan Hedman, Peter Ben Mildenhall Xu, dejia Barron, Jonathan T. Wang, Zhangyang Xue, Tianfan Univ Texas Austin Austin TX 78712 USA Google Res Mountain View CA USA Chinese Univ Hong Kong Hong Kong Peoples R China Google Mountain View CA USA

ISBN: (纸本)9798350301298

Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3d scene as a continuous function. Though NeRF is able to render complex 3d scenes with view-dependent effects, few efforts have been devoted to exploring its limits in a high-resolution setting. Specifically, existing NeRF-based methods face several limitations when reconstructing high-resolution real scenes, including a very large number of parameters, misaligned input data, and overly smooth details. In this work, we conduct the first pilot study on training NeRF with highresolution data and propose the corresponding solutions: 1) marrying the multilayer perceptron (MLP) with convolutional layers which can encode more neighborhood information while reducing the total number of parameters;2) a novel training strategy to address misalignment caused by moving objects or small camera calibration errors;and 3) a high-frequency aware loss. Our approach is nearly free without introducing obvious training/testing costs, while experiments on different datasets demonstrate that it can recover more high-frequency details compared with the current state-of-the-art NeRF models. Project page: https: //***/alignerf.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

Fully Self-Supervised depth Estimation from defocus Clue

Fully Self-Supervised Depth Estimation from Defocus Clue

引用

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

作者： Si, Haozhe Zhao, Bin Wang, dong Gao, Yunpeng Chen, Mulin Wang, Zhigang Li, Xuelong Shanghai AI Lab Shanghai Peoples R China Univ Illinois Champaign IL USA Northwestern Polytech Univ Grande Prairie AB Canada

ISBN: (纸本)9798350301298

depth-from-defocus (dFd), modeling the relationship between depth and defocus pattern in images, has demonstrated promising performance in depth estimation. Recently, several self-supervised works try to overcome the difficulties in acquiring accurate depth ground-truth. However, they depend on the all-in-focus (AIF) images, which cannot be captured in real-world scenarios. Such limitation discourages the applications of dFd methods. To tackle this issue, we propose a completely self-supervised framework that estimates depth purely from a sparse focal stack. We show that our framework circumvents the needs for the depth and AIF image ground-truth, and receives superior predictions, thus closing the gap between the theoretical success of dFd works and their applications in the real world. In particular, we propose (i) a more realistic setting for dFd tasks, where no depth or AIF image ground-truth is available;(ii) a novel self-supervision framework that provides reliable predictions of depth and AIF image under the challenging setting. The proposed framework uses a neural model to predict the depth and AIF image, and utilizes an optical model to validate and refine the prediction. We verify our framework on three benchmark datasets with rendered focal stacks and real focal stacks. Qualitative and quantitative evaluations show that our method provides a strong baseline for self-supervised dFd tasks. The source code is publicly available at https://***/Ehzoahis/dERed.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

NoPe-NeRF: Optimising Neural Radiance Field with No Pose Pri...

引用

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

作者： Bian, Wenjing Wang, Zirui Li, Kejie Bian, Jia-Wang Prisacariu, Victor Adrian Univ Oxford Act Vis Lab Oxford England

ISBN: (纸本)9798350301298

Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy. Our project page is https://***.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

CompletionFormer: depth Completion with Convolutions and Vision Transformers

CompletionFormer: Depth Completion with Convolutions and Vis...

引用

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

作者： Zhang, Youmin Guo, Xianda Poggi, Matteo Zhu, Zheng Huang, Guan Mattoccia, Stefano Univ Bologna Bologna Italy PhiGent Robot Beijing Peoples R China

ISBN: (纸本)9798350301298

Given sparse depths and the corresponding RGB images, depth completion aims at spatially propagating the sparse measurements throughout the whole image to get a dense depth prediction. despite the tremendous progress of deep-learning-based depth completion methods, the locality of the convolutional layer or graph model makes it hard for the network to model the long-range relationship between pixels. While recent fully Transformer-based architecture has reported encouraging results with the global receptive field, the performance and efficiency gaps to the well-developed CNN models still exist because of its deteriorative local feature details. This paper proposes a Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct our depth completion model in a pyramidal structure. This hybrid architecture naturally benefits both the local connectivity of convolutions and the global context of the Transformer in one single model. As a result, our Completion-Former outperforms state-of-the-art CNNs-based methods on the outdoor KITTI depth Completion benchmark and indoor NYUv2 dataset, achieving significantly higher efficiency (nearly 1/3 FLOPs) compared to pure Transformer-based methods. Code is available at https://***/youmi-zym/CompletionFormer.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections

Looking Through the Glass: Neural Surface Reconstruction Aga...

引用

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

作者： Qiu, Jiaxiong Jiang, Peng-Tao Zhu, Yifan Yin, Ze-Xin Cheng, Ming-Ming Ren, Bo Nankai Univ CS VCIP Tianjin Peoples R China Zhejiang Univ Hangzhou Peoples R China

ISBN: (纸本)9798350301298

Neural implicit methods have achieved high-quality 3d object surfaces under slight specular highlights. However, high specular reflections (HSR) often appear in front of target objects when we capture them through glasses. The complex ambiguity in these scenes violates the multi-view consistency, then makes it challenging for recent methods to reconstruct target objects correctly. To remedy this issue, we present a novel surface reconstruction framework, NeuS-HSR, based on implicit neural rendering. In NeuSHSR, the object surface is parameterized as an implicit signed distance function (SdF). To reduce the interference of HSR, we propose decomposing the rendered image into two appearances: the target object and the auxiliary plane. We design a novel auxiliary plane module by combining physical assumptions and neural networks to generate the auxiliary plane appearance. Extensive experiments on synthetic and real-world datasets demonstrate that NeuS-HSR outperforms state-of-the-art approaches for accurate and robust target surface reconstruction against HSR. Code is available at https://***/JiaxiongQ/NeuS-HSR.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

Learning Transformation-Predictive Representations for detection and description of Local Features

Learning Transformation-Predictive Representations for Detec...

引用

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

作者： Wang, Zihao Wu, Chunxu Yang, Yifei Li, Zhen Peking Univ Sch Intelligence Sci & Technol Beijing Peoples R China Beijing Inst Technol Sch Automat Beijing Peoples R China

ISBN: (纸本)9798350301298

The task of key-points detection and description is to estimate the stable location and discriminative representation of local features, which is a fundamental task in visual applications. However, either the rough hard positive or negative labels generated from one-to-one correspondences among images may bring indistinguishable samples, like false positives or negatives, which acts as inconsistent supervision. Such resultant false samples mixed with hard samples prevent neural networks from learning descriptions for more accurate matching. To tackle this challenge, we propose to learn the transformation-predictive representations with self-supervised contrastive learning. We maximize the similarity between corresponding views of the same 3d point (landmark) by using none of the negative sample pairs and avoiding collapsing solutions. Furthermore, we adopt self-supervised generation learning and curriculum learning to soften the hard positive labels into soft continuous targets. The aggressively updated soft labels contribute to overcoming the training bottleneck (derived from the label noise of false positives) and facilitating the model training under a stronger transformation paradigm. Our self-supervised training pipeline greatly decreases the computation load and memory usage, and outperforms the sota on the standard image matching benchmarks by noticeable margins, demonstrating excellent generalization capability on multiple downstream tasks.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

CLIP²: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud data

CLIP<SUP>2</SUP>: Contrastive Language-Image-Point Pretraini...

引用

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

作者： Zeng, Yihan Jiang, Chenhan Mao, Jiageng Han, Jianhua Ye, Chaoqiang Huang, Qingqiu Yeung, dit-Yan Yang, Zhen Liang, Xiaodan Xu, Hang Huawei Noahs Ark Lab Montreal PQ Canada Hong Kong Univ Sci & Technol Hong Kong Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Sun Yat San Univ Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks. However, due to the limited Text-3d data pairs, adapting the success of 2d Vision-Language Models (VLM) to the 3d space remains an open problem. Existing works that leverage VLM for 3d understanding generally resort to constructing intermediate 2d representations for the 3d data, but at the cost of losing 3d geometry information. To take a step toward open-world 3d vision understanding, we propose Contrastive Language-Image-Point Cloud Pretraining (CLIP2) to directly learn the transferable 3d point cloud representation in realistic scenarios with a novel proxy alignment mechanism. Specifically, we exploit naturally-existed correspondences in 2d and 3d scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios. On top of that, we propose a cross-modal contrastive objective to learn semantic and instance-level aligned point cloud representation. Experimental results on both indoor and outdoor scenarios show that our learned 3d representation has great transfer ability in downstream tasks, including zero-shot and few-shot 3d recognition, which boosts the state-of-the-art methods by large margins. Furthermore, we provide analyses of the capability of different representations in real scenarios and present the optional ensemble scheme.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

Learning 3d Representations from 2d Pre-trained Models via Image-to-Point Masked Autoencoders

Learning 3D Representations from 2D Pre-trained Models via I...

引用

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

作者： Zhang, Renrui Wang, Liuhui Qiao, Yu Gao, Peng Li, Hongsheng Shanghai Artificial Intelligence Lab Shanghai Peoples R China CUHK MMLab Hong Kong Peoples R China Peking Univ Beijing Peoples R China CPII InnoHK Hong Kong Peoples R China

ISBN: (纸本)9798350301298

Pre-training by numerous image data has become de-facto for robust 2d representations. In contrast, due to the expensive data processing, a paucity of 3d datasets severely hinders the learning for high-quality 3d features. In this paper, we propose an alternative to obtain superior 3d representations from 2d pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2d knowledge to guide 3d masked autoencoding, which reconstructs the masked point tokens with an encoder-decoder architecture. Specifically, we first utilize off-the-shelf 2d models to extract the multi-view visual features of the input point cloud, and then conduct two types of image-to-point learning schemes. For one, we introduce a 2d-guided masking strategy that maintains semantically important point tokens to be visible. Compared to random masking, the network can better concentrate on significant 3d structures with key spatial cues. For another, we enforce these visible tokens to reconstruct multi-view 2d features after the decoder. This enables the network to effectively inherit high-level 2d semantics for discriminative 3d modeling. Aided by our image-to-point pre-training, the frozen I2P-MAE, without any fine-tuning, achieves 93.4% accuracy for linear SVM on ModelNet40, competitive to existing fully trained methods. By further fine-tuning on on ScanObjectNN's hardest split, I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity. Code is available at https://***/ZrrSkywalker/I2P-MAE.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

NeRFLiX: High-Quality Neural view Synthesis by Learning a degradation-driven Inter-viewpoint MiXer

NeRFLiX: High-Quality Neural View Synthesis by Learning a De...

引用

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

作者： Zhou, Kun Li, Wenbo Wang, Yi Hu, Tao Jiang, Nianjuan Han, Xiaoguang Lu, Jiangbo CUHK Shenzhen SSE Shenzhen Peoples R China SmartMore Corp Hong Kong Peoples R China CUHK Hong Kong Peoples R China Shanghai AI Lab Shanghai Peoples R China

ISBN: (纸本)9798350301298

Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise, blur, etc. Towards to improve the synthesis quality of NeRF-based approaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for existing deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.

关键词： 3d from multi-view and sensors

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共25页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：