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61-70 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：

IterativePFN: True Iterative Point Cloud Filtering

IterativePFN: True Iterative Point Cloud Filtering

引用

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

作者： Edirimuni, dasith de Silva Lu, Xuequan Shao, Zhiwen Li, Gang Robles-Kelly, Antonio He, Ying Deakin Univ Sch Informat Technol Geelong Vic Australia China Univ Min & Technol Sch Comp Sci & Technol Beijing Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Def Sci & Technol Grp Edinburgh Australia

ISBN: (纸本)9798350301298

The quality of point clouds is often limited by noise introduced during their capture process. Consequently, a fundamental 3d vision task is the removal of noise, known as point cloud filtering or denoising. State-of-the-art learning based methods focus on training neural networks to infer filtered displacements and directly shift noisy points onto the underlying clean surfaces. In high noise conditions, they iterate the filtering process. However, this iterative filtering is only done at test time and is less effective at ensuring points converge quickly onto the clean surfaces. We propose IterativePFN (iterative point cloud filtering network), which consists of multiple IterationModules that model the true iterative filtering process internally, within a single network. We train our IterativePFN network using a novel loss function that utilizes an adaptive ground truth target at each iteration to capture the relationship between intermediate filtering results during training. This ensures that the filtered results converge faster to the clean surfaces. Our method is able to obtain better performance compared to state-of-the-art methods. The source code can be found at: https: //***/ddsediri/IterativePFN.

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

Shakes on a Plane: Unsupervised depth Estimation from Unstabilized Photography

Shakes on a Plane: Unsupervised Depth Estimation from Unstab...

引用

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

作者： Chugunov, Ilya Zhang, Yuxuan Heide, Felix Princeton Univ Princeton NJ 08544 USA

ISBN: (纸本)9798350301298

Modern mobile burst photography pipelines capture and merge a short sequence of frames to recover an enhanced image, but often disregard the 3d nature of the scene they capture, treating pixel motion between images as a 2d aggregation problem. We show that in a "long-burst", fortytwo 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. To this end, we devise a test-time optimization approach that fits a neural RGB-d representation to long-burst data and simultaneously estimates scene depth and camera motion. Our plane plus depth model is trained end-to-end, and performs coarse-to-fine refinement by controlling which multi-resolution volume features the network has access to at what time during training. We validate the method experimentally, and demonstrate geometrically accurate depth reconstructions with no additional hardware or separate data pre-processing and pose-estimation steps.

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

Neural Fields meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

Neural Fields meet Explicit Geometric Representations for In...

引用

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

作者： Wang, Zian Shen, Tianchang Gao, Jun Huang, Shengyu Munkberg, Jacob Hasselgren, Jon Gojcic, Zan Chen, Wenzheng Fidler, Sanja NVIDIA Santa Clara CA 95050 USA Univ Toronto Toronto ON M5S 1A1 Canada Vector Inst Ameerpet India Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9798350301298

Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3d reconstruction, but bake the lighting and shadows into the radiance field, while mesh-based methods that facilitate intrinsic decomposition through differentiable rendering have not yet scaled to the complexity and scale of outdoor scenes. We present a novel inverse rendering framework for large urban scenes capable of jointly reconstructing the scene geometry, spatially-varying materials, and HdR lighting from a set of posed RGB images with optional depth. Specifically, we use a neural field to account for the primary rays, and use an explicit mesh (reconstructed from the underlying neural field) for modeling secondary rays that produce higher-order lighting effects such as cast shadows. By faithfully disentangling complex geometry and materials from lighting effects, our method enables photorealistic relighting with specular and shadow effects on several outdoor datasets. Moreover, it supports physics-based scene manipulations such as virtual object insertion with ray-traced shadow casting.

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

PVO: Panoptic Visual Odometry

PVO: Panoptic Visual Odometry

引用

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

作者： Ye, Weicai Lan, Xinyue Chen, Shuo Ming, Yuhang Yu, Xingyuan Bao, Hujun Cui, Zhaopeng Zhang, Guofeng Zhejiang Univ State Key Lab CAD&CG Hangzhou Zhejiang Peoples R China ZJU SenseTime Joint Lab 3D Vis Hangzhou Zhejiang Peoples R China Hangzhou Dianzi Univ Sch Comp Sci Hangzhou Peoples R China Univ Bristol VIL Bristol Avon England

ISBN: (纸本)9798350301298

We present PVO, a novel panoptic visual odometry framework to achieve more comprehensive modeling of the scene motion, geometry, and panoptic segmentation information. Our PVO models visual odometry (VO) and video panoptic segmentation (VPS) in a unified view, which makes the two tasks mutually beneficial. Specifically, we introduce a panoptic update module into the VO Module with the guidance of image panoptic segmentation. This Panoptic-Enhanced VO Module can alleviate the impact of dynamic objects in the camera pose estimation with a panoptic-aware dynamic mask. On the other hand, the VO-Enhanced VPS Module also improves the segmentation accuracy by fusing the panoptic segmentation result of the current frame on the fly to the adjacent frames, using geometric information such as camera pose, depth, and optical flow obtained from the VO Module. These two modules contribute to each other through recurrent iterative optimization. Extensive experiments demonstrate that PVO outperforms state-of-the-art methods in both visual odometry and video panoptic segmentation 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

Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-d Scans

Neural Part Priors: Learning to Optimize Part-Based Object C...

引用

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

作者： Bokhovkin, Aleksei dai, Angela Tech Univ Munich Munich Germany

ISBN: (纸本)9798350301298

3d scene understanding has seen significant advances in recent years, but has largely focused on object understanding in 3d scenes with independent per-object predictions. We thus propose to learn Neural Part Priors (NPPs), parametric spaces of objects and their parts, that enable optimizing to fit to a new input 3d scan with global scene consistency constraints. The rich structure of our NPPs enables accurate, holistic scene reconstruction across similar objects in the scene. Both objects and their part geometries are characterized by coordinate field MLPs, facilitating optimization at test time to fit to input geometric observations as well as similar objects in the input scan. This enables more accurate reconstructions than independent per-object predictions as a single forward pass, while establishing global consistency within a scene. Experiments on the ScanNet dataset demonstrate that NPPs significantly outperforms the state-of-the-art in part decomposition and object completion in real-world scenes.

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

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for multi-view Stereo

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-...

引用

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

作者： Cai, Changjiang Ji, Pan Yan, Qingan Xu, Yi InnoPeak Technol Inc OPPO US Res Ctr Palo Alto CA 94303 USA

ISBN: (纸本)9798350301298

This paper presents a learning-based method for multi-view depth estimation from posed images. Our core idea is a "learning-to-optimize" paradigm that iteratively indexes a plane-sweeping cost volume and regresses the depth map via a convolutional Gated Recurrent Unit (GRU). Since the cost volume plays a paramount role in encoding the multi-view geometry, we aim to improve its construction both at pixel- and frame- levels. At the pixel level, we propose to break the symmetry of the Siamese network (which is typically used in MVS to extract image features) by introducing a transformer block to the reference image (but not to the source images). Such an asymmetric volume allows the network to extract global features from the reference image to predict its depth map. Given potential inaccuracies in the poses between reference and source images, we propose to incorporate a residual pose network to correct the relative poses. This essentially rectifies the cost volume at the frame level. We conduct extensive experiments on real-world MVS datasets and show that our method achieves state-of-the-art performance in terms of both within-dataset evaluation and cross-dataset generalization.

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

Self-supervised Super-plane for Neural 3d Reconstruction

Self-supervised Super-plane for Neural 3D Reconstruction

引用

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

作者： Ye, Botao Liu, Sifei Li, Xueting Yang, Ming-Hsuan Univ Chinese Acad Sci Beijing Peoples R China NVIDIA Santa Clara CA USA Univ Calif Merced Merced CA USA Yonsei Univ Seoul South Korea

ISBN: (纸本)9798350301298

Neural implicit surface representation methods show impressive reconstruction results but struggle to handle texture-less planar regions that widely exist in indoor scenes. Existing approaches addressing this leverage image prior that requires assistive networks trained with large-scale annotated datasets. In this work, we introduce a self-supervised super-plane constraint by exploring the free geometry cues from the predicted surface, which can further regularize the reconstruction of plane regions without any other ground truth annotations. Specifically, we introduce an iterative training scheme, where (i) grouping of pixels to formulate a super-plane (analogous to superpixels), and (ii) optimizing of the scene reconstruction network via a super-plane constraint, are progressively conducted. We demonstrate that the model trained with superplanes surprisingly outperforms the one using conventional annotated planes, as individual super-plane statistically occupies a larger area and leads to more stable training. Extensive experiments show that our self-supervised superplane constraint significantly improves 3d reconstruction quality even better than using ground truth plane segmentation. Additionally, the plane reconstruction results from our model can be used for auto-labeling for other vision tasks. The code and models are available at https: //***/botaoye/S3PRecon.

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

Unsupervised deep Asymmetric Stereo Matching with Spatially-Adaptive Self-Similarity

Unsupervised Deep Asymmetric Stereo Matching with Spatially-...

引用

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

作者： Song, Taeyong Kim, Sunok Sohn, Kwanghoon Hyundai Motor Co R&D Div Seoul South Korea Korea Aerosp Univ Goyang South Korea Yonsei Univ Seoul South Korea Korea Inst Sci & Technol KIST Seoul South Korea

ISBN: (纸本)9798350301298

Unsupervised stereo matching has received a lot of attention since it enables the learning of disparity estimation without ground-truth data. However, most of the unsupervised stereo matching algorithms assume that the left and right images have consistent visual properties, i.e., symmetric, and easily fail when the stereo images are asymmetric. In this paper, we present a novel spatially-adaptive self-similarity (SASS) for unsupervised asymmetric stereo matching. It extends the concept of self-similarity and generates deep features that are robust to the asymmetries. The sampling patterns to calculate self-similarities are adaptively generated throughout the image regions to effectively encode diverse patterns. In order to learn the effective sampling patterns, we design a contrastive similarity loss with positive and negative weights. Consequently, SASS is further encouraged to encode asymmetry-agnostic features, while maintaining the distinctiveness for stereo correspondence. We present extensive experimental results including ablation studies and comparisons with different methods, demonstrating effectiveness of the proposed method under resolution and noise asymmetries.

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

Four-view Geometry with Unknown Radial distortion

Four-view Geometry with Unknown Radial Distortion

引用

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

作者： Hruby, Petr Korotynskiy, Viktor duff, Timothy Oeding, Luke Pollefeys, Marc Pajdla, Tomas Larsson, Viktor Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Czech Tech Univ CIIRC Prague Czech Republic Univ Washington Seattle WA USA Auburn Univ Auburn AL USA Lund Univ Lund Sweden

ISBN: (纸本)9798350301298

We present novel solutions to previously unsolved problems of relative pose estimation from images whose calibration parameters, namely focal lengths and radial distortion, are unknown. Our approach enables metric reconstruction without modeling these parameters. The minimal case for reconstruction requires 13 points in 4 views for both the calibrated and uncalibrated cameras. We describe and implement the first solution to these minimal problems. In the calibrated case, this may be modeled as a polynomial system of equations with 3584 solutions. despite the apparent intractability, the problem decomposes spectacularly. Each solution falls into a Euclidean symmetry class of size 16, and we can estimate 224 class representatives by solving a sequence of three subproblems with 28, 2, and 4 solutions. We highlight the relationship between internal constraints on the radial quadrifocal tensor and the relations among the principal minors of a 4 x 4 matrix. We also address the case of 4 upright cameras, where 7 points are minimal. Finally, we evaluate our approach on simulated and real data and benchmark against previous calibration-free solutions, and show that our method provides an efficient startup for an SfM pipeline with radial cameras. [GRAPHICS] .

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

BAEFormer: Bi-directional and Early Interaction Transformers for Bird's Eye view Semantic Segmentation

BAEFormer: Bi-directional and Early Interaction Transformers...

引用

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

作者： Pan, Cong He, Yonghao Peng, Junran Zhang, Qian Sui, Wei Zhang, Zhaoxiang Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China Univ Chinese Acad Sci Sch Future Technol Beijing Peoples R China Horizon Robot Beijing Peoples R China Huawei Inc Shenzhen Guangdong Peoples R China HKISI CAS Ctr Artificial Intelligence & Robot Beijing Peoples R China

ISBN: (纸本)9798350301298

Bird's Eye view (BEV) semantic segmentation is a critical task in autonomous driving. However, existing Transformer-based methods confront difficulties in transforming Perspective view (PV) to BEV due to their unidirectional and posterior interaction mechanisms. To address this issue, we propose a novel Bi-directional and Early Interaction Transformers framework named BAEFormer, consisting of (i) an early-interaction PV-BEV pipeline and (ii) a bi-directional cross-attention mechanism. Moreover, we find that the image feature maps' resolution in the cross-attention module has a limited effect on the final performance. Under this critical observation, we propose to enlarge the size of input images and downsample the multiview image features for cross-interaction, further improving the accuracy while keeping the amount of computation controllable. Our proposed method for BEV semantic segmentation achieves state-of-the-art performance in real-time inference speed on the nuScenes dataset, i.e., 38.9 mIoU at 45 FPS on a single A100 GPU.

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 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：