3D 视觉 - arXivDaily 专题

2203.09457 2022-03-18 cs.CV 57%

Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image

Xuanchi Ren, Xiaolong Wang

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Accepted to CVPR 2022. Project page: https://xrenaa.github.io/look-outside-room/

2201.12425 2022-02-01 cs.CV cs.LG 57%

CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture

Ruofan Liang, Hongyi Sun, Nandita Vijaykumar

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2008.12606 2021-12-01 cs.CV 57%

Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation

Yurui Ren, Ge Li, Shan Liu, Thomas H. Li

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:2003.00696

2111.14741 2021-11-30 cs.CV 57%

Domain Adaptation of Networks for Camera Pose Estimation: Learning Camera Pose Estimation Without Pose Labels

Jack Langerman, Ziming Qiu, Gábor Sörös, Dávid Sebők, Yao Wang, Howard Huang

专题命中新视角合成：point cloud(abstract)；分类 cs.CV

2007.00323 2021-10-25 cs.CV cs.CG 57%

Future Urban Scenes Generation Through Vehicles Synthesis

Alessandro Simoni, Luca Bergamini, Andrea Palazzi, Simone Calderara, Rita Cucchiara

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Accepted at ICPR2020

2104.04073 2021-10-15 cs.CV 57%

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

Shuai Chen, Zirui Wang, Victor Prisacariu

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2110.02951 2021-10-07 cs.CV cs.LG 57%

Video Autoencoder: self-supervised disentanglement of static 3D structure and motion

Zihang Lai, Sifei Liu, Alexei A. Efros, Xiaolong Wang

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Accepted to ICCV 2021. Project page: https://zlai0.github.io/VideoAutoencoder

2109.00249 2021-09-02 cs.CV 57%

Seeing Implicit Neural Representations as Fourier Series

Nuri Benbarka, Timon Höfer, Hamd ul-moqeet Riaz, Andreas Zell

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2108.13003 2021-08-31 cs.CV 57%

Embedding Novel Views in a Single JPEG Image

Yue Wu, Guotao Meng, Qifeng Chen

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments published in ICCV 2021; Supplementary material will be added later

2108.05892 2021-08-13 cs.CV 57%

PixelSynth: Generating a 3D-Consistent Experience from a Single Image

Chris Rockwell, David F. Fouhey, Justin Johnson

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments In ICCV 2021

2107.05113 2021-07-13 cs.CV 57%

LiveView: Dynamic Target-Centered MPI for View Synthesis

Sushobhan Ghosh, Zhaoyang Lv, Nathan Matsuda, Lei Xiao, Andrew Berkovich, Oliver Cossairt

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2105.06468 2021-05-14 cs.CV 57%

Dynamic View Synthesis from Dynamic Monocular Video

Chen Gao, Ayush Saraf, Johannes Kopf, Jia-Bin Huang

专题命中新视角合成：NeRF(abstract)；分类 cs.CV

Comments Project webpage: https://free-view-video.github.io/

2104.01508 2021-05-11 cs.CV 57%

Learning Neural Representation of Camera Pose with Matrix Representation of Pose Shift via View Synthesis

Yaxuan Zhu, Ruiqi Gao, Siyuan Huang, Song-Chun Zhu, Ying Nian Wu

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2105.00125 2021-05-04 cs.CV 57%

Sparse Pose Trajectory Completion

Bo Liu, Mandar Dixit, Roland Kwitt, Gang Hua, Nuno Vasconcelos

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2102.13090 2021-04-08 cs.CV 57%

IBRNet: Learning Multi-View Image-Based Rendering

Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, Thomas Funkhouser

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments CVPR 2021. Project page: https://ibrnet.github.io/

2103.02852 2021-04-06 cs.CV 57%

Data Augmentation for Object Detection via Differentiable Neural Rendering

Guanghan Ning, Guang Chen, Chaowei Tan, Si Luo, Liefeng Bo, Heng Huang

专题命中新视角合成：point cloud(abstract)；分类 cs.CV

Comments 15 pages, 15 figures

2009.02978 2021-04-06 cs.CV 57%

Light Field View Synthesis via Aperture Disparity and Warping Confidence Map

Nan Meng, Kai Li, Jianzhuang Liu, Edmund Y. Lam

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments 14 pages, 14 figures

Journal ref IEEE Transactions on Image Processing 30 (2021): 3908-3921

1912.03249 2021-03-05 stat.ML cs.CV cs.LG 57%

Gaussian Process Priors for View-Aware Inference

Yuxin Hou, Ari Heljakka, Arno Solin

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Appearing in AAAI 2021

2102.11263 2021-02-23 cs.CV 57%

Style and Pose Control for Image Synthesis of Humans from a Single Monocular View

Kripasindhu Sarkar, Vladislav Golyanik, Lingjie Liu, Christian Theobalt

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2004.07484 2020-12-23 cs.GR 57%

Pulsar: Efficient Sphere-based Neural Rendering

Christoph Lassner, Michael Zollhöfer

专题命中新视角合成：3D reconstruction(abstract)；分类 cs.GR

2011.13317 2020-11-30 cs.CV 57%

Adaptive Multiplane Image Generation from a Single Internet Picture

Diogo C. Luvizon, Gustavo Sutter P. Carvalho, Andreza A. dos Santos, Jhonatas S. Conceicao, Jose L. Flores-Campana, Luis G. L. Decker, Marcos R. Souza, Helio Pedrini, Antonio Joia, Otavio A. B. Penatti

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2010.03169 2020-10-08 cs.MM cs.GR 57%

Haptic Rendering of Cultural Heritage Objects at Different Scales

Sreeni K. G, Priyadarshini K, Praseedha A. K, Subhasis Chaudhuri

专题命中新视角合成：point cloud(abstract)；分类 cs.GR

Comments Accepted to EuroHaptics. arXiv admin note: text overlap with arXiv:2010.02015

2010.02015 2020-10-06 cs.MM cs.GR 57%

Combined Hapto-Visual and Auditory Rendering of Cultural Heritage Objects

Praseedha Krishnan Aniyath, Sreeni Kamalalayam Gopalan, Priyadarshini K, Subhasis Chaudhuri

专题命中新视角合成：point cloud(abstract)；分类 cs.GR

Comments Accepted to ACCVw 2014

2004.04548 2020-09-23 cs.CV cs.LG eess.IV 57%

Sequential View Synthesis with Transformer

Phong Nguyen-Ha, Lam Huynh, Esa Rahtu, Janne Heikkila

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Code is available at: https://github.com/phongnhhn92/TransformerGQN; Supplementary material: https://bit.ly/3kEgnzU

2008.05511 2020-08-14 cs.CV 57%

Free View Synthesis

Gernot Riegler, Vladlen Koltun

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments published at ECCV 2020, https://youtu.be/JDJPn3ZtfZs

2007.15194 2020-07-31 cs.CV 57%

Crowdsampling the Plenoptic Function

Zhengqi Li, Wenqi Xian, Abe Davis, Noah Snavely

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments ECCV, 2020 (Oral)

2007.10300 2020-07-22 cs.CV 57%

Object-Centric Multi-View Aggregation

Shubham Tulsiani, Or Litany, Charles R. Qi, He Wang, Leonidas J. Guibas

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

2004.04727 2020-06-11 cs.CV eess.IV 57%

3D Photography using Context-aware Layered Depth Inpainting

Meng-Li Shih, Shih-Yang Su, Johannes Kopf, Jia-Bin Huang

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments CVPR 2020. Project page: https://shihmengli.github.io/3D-Photo-Inpainting/ Code: https://github.com/vt-vl-lab/3d-photo-inpainting Demo: https://colab.research.google.com/drive/1706ToQrkIZshRSJSHvZ1RuCiM__YX3Bz

1912.08804 2020-04-21 cs.CV 57%

SynSin: End-to-end View Synthesis from a Single Image

Olivia Wiles, Georgia Gkioxari, Richard Szeliski, Justin Johnson

专题命中新视角合成：point cloud(abstract)；分类 cs.CV

Comments Project page: www.robots.ox.ac.uk/~ow/synsin.html

1906.01618 2020-01-30 cs.CV cs.AI 57%

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

Vincent Sitzmann, Michael Zollhöfer, Gordon Wetzstein

专题命中新视角合成：novel view synthesis(abstract)；分类 cs.CV

Comments Video: https://youtu.be/6vMEBWD8O20 Project page: https://vsitzmann.github.io/srns/

1. 新视角合成 733 篇

Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image

CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture

Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation

Domain Adaptation of Networks for Camera Pose Estimation: Learning Camera Pose Estimation Without Pose Labels

Future Urban Scenes Generation Through Vehicles Synthesis

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

Video Autoencoder: self-supervised disentanglement of static 3D structure and motion

Seeing Implicit Neural Representations as Fourier Series

Embedding Novel Views in a Single JPEG Image

PixelSynth: Generating a 3D-Consistent Experience from a Single Image

LiveView: Dynamic Target-Centered MPI for View Synthesis

Dynamic View Synthesis from Dynamic Monocular Video

Learning Neural Representation of Camera Pose with Matrix Representation of Pose Shift via View Synthesis

Sparse Pose Trajectory Completion

IBRNet: Learning Multi-View Image-Based Rendering

Data Augmentation for Object Detection via Differentiable Neural Rendering

Light Field View Synthesis via Aperture Disparity and Warping Confidence Map

Gaussian Process Priors for View-Aware Inference

Style and Pose Control for Image Synthesis of Humans from a Single Monocular View

Pulsar: Efficient Sphere-based Neural Rendering

Adaptive Multiplane Image Generation from a Single Internet Picture

Haptic Rendering of Cultural Heritage Objects at Different Scales

Combined Hapto-Visual and Auditory Rendering of Cultural Heritage Objects

Sequential View Synthesis with Transformer

Free View Synthesis

Crowdsampling the Plenoptic Function

Object-Centric Multi-View Aggregation

3D Photography using Context-aware Layered Depth Inpainting

SynSin: End-to-end View Synthesis from a Single Image

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations