3D 视觉 - arXivDaily 专题

2304.05620 2023-04-13 cs.CV 57%

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

Chi-en Amy Tai, Jason Li, Sriram Kumar, Saeejith Nair, Yuhao Chen, Pengcheng Xi, Alexander Wong

专题命中新视角合成：NeRF(abstract)；分类 cs.CV

2304.04188 2023-04-11 cs.GR cs.LG 57%

HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation

Qi Wu, David Bauer, Yuyang Chen, Kwan-Liu Ma

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

2304.03184 2023-04-07 cs.CV 57%

Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream

Yuheng Jiang, Kaixin Yao, Zhuo Su, Zhehao Shen, Haimin Luo, Lan Xu

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

Comments CVPR 2023

2303.18139 2023-04-06 cs.CV 57%

Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations

Thomas Tanay, Aleš Leonardis, Matteo Maggioni

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

Comments Accepted at CVPR 2023

2303.17598 2023-03-31 cs.CV 57%

Consistent View Synthesis with Pose-Guided Diffusion Models

Hung-Yu Tseng, Qinbo Li, Changil Kim, Suhib Alsisan, Jia-Bin Huang, Johannes Kopf

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

Comments CVPR 2023. Project page: https://poseguided-diffusion.github.io/

2212.01206 2023-03-28 cs.CV 57%

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Norman Müller, Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Matthias Nießner

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

Comments Project page: https://sirwyver.github.io/DiffRF/ Video: https://youtu.be/qETBcLu8SUk - CVPR 2023 Highlight - updated evaluations after fixing initial data mapping error on all methods

2303.14368 2023-03-28 cs.CV cs.AI cs.LG 57%

FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views

Vinoj Jayasundara, Amit Agrawal, Nicolas Heron, Abhinav Shrivastava, Larry S. Davis

专题命中新视角合成：NeRF(abstract)；分类 cs.CV

Comments CVPR 2023

2211.10206 2023-03-22 cs.CV 57%

Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes

Zhen Li, Lingli Wang, Mofang Cheng, Cihui Pan, Jiaqi Yang

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

Comments Accepted to CVPR 2023. The project page is at: https://lzleejean.github.io/TexIR

2211.13901 2023-03-21 cs.CV 57%

Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image

Yu Deng, Baoyuan Wang, Heung-Yeung Shum

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

Comments CVPR 2023 camera-ready version. Project page: https://yudeng.github.io/GRAMInverter/

2201.09023 2023-01-31 cs.CV 57%

Content-aware Warping for View Synthesis

Mantang Guo, Junhui Hou, Jing Jin, Hui Liu, Huanqiang Zeng, Jiwen Lu

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:2108.07408

2301.11326 2023-01-27 cs.CV 57%

Unsupervised Volumetric Animation

Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Kyle Olszewski, Jian Ren, Hsin-Ying Lee, Menglei Chai, Sergey Tulyakov

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

2211.16991 2022-12-01 cs.CV 57%

SparsePose: Sparse-View Camera Pose Regression and Refinement

Samarth Sinha, Jason Y. Zhang, Andrea Tagliasacchi, Igor Gilitschenski, David B. Lindell

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

2211.15662 2022-11-30 cs.CV 57%

High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization

Jiaxin Xie, Hao Ouyang, Jingtan Piao, Chenyang Lei, Qifeng Chen

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

Comments Project website: https://ken-ouyang.github.io/HFGI3D/index.html ; Github link: https://github.com/jiaxinxie97/HFGI3D

2211.15059 2022-11-29 cs.CV 57%

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

Stefan Stojanov, Anh Thai, Zixuan Huang, James M. Rehg

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

Comments Accepted at NeurIPS 2022. Code and data available at https://github.com/rehg-lab/dope_selfsup

2206.07695 2022-11-11 cs.CV 57%

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Katja Schwarz, Axel Sauer, Michael Niemeyer, Yiyi Liao, Andreas Geiger

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

2206.06922 2022-10-13 cs.CV cs.AI cs.LG 57%

Object Scene Representation Transformer

Mehdi S. M. Sajjadi, Daniel Duckworth, Aravindh Mahendran, Sjoerd van Steenkiste, Filip Pavetić, Mario Lučić, Leonidas J. Guibas, Klaus Greff, Thomas Kipf

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

Comments Accepted at NeurIPS '22. Project page: https://osrt-paper.github.io/

2210.04572 2022-10-11 cs.CV 57%

Floorplan-Aware Camera Poses Refinement

Anna Sokolova, Filipp Nikitin, Anna Vorontsova, Anton Konushin

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

Comments IROS 2022

2106.09548 2022-10-05 cs.CV 57%

Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

Wenpeng Xing, Jie Chen, Zaifeng Yang, Qiang Wang

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

2111.10533 2022-08-09 cs.CV 57%

Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning

Wenpeng Xing, Jie Chen

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

Comments In ECCV 2022

2207.12579 2022-07-27 cs.CV 57%

RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments

Jiahui Zhang, Shitao Tang, Kejie Qiu, Rui Huang, Chuan Fang, Le Cui, Zilong Dong, Siyu Zhu, Ping Tan

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

2205.02084 2022-07-27 cs.CV cs.AI 57%

Video Extrapolation in Space and Time

Yunzhi Zhang, Jiajun Wu

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

Comments ECCV 2022. Project page: https://cs.stanford.edu/~yzzhang/projects/vest/

2204.00559 2022-07-21 cs.CV 57%

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

Shuai Chen, Xinghui Li, Zirui Wang, Victor Adrian Prisacariu

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

Comments ECCV 2022. Code released at https://github.com/ActiveVisionLab/DFNet

2206.06481 2022-06-15 cs.CV 57%

RigNeRF: Fully Controllable Neural 3D Portraits

ShahRukh Athar, Zexiang Xu, Kalyan Sunkavalli, Eli Shechtman, Zhixin Shu

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

Comments The project page can be found here: http://shahrukhathar.github.io/2022/06/06/RigNeRF.html

2106.13139 2022-05-16 cs.CV 57%

FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending

Andre Rochow, Max Schwarz, Michael Weinmann, Sven Behnke

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

Comments Accepted to Robotics: Science and Systems (RSS) 2022

2205.05509 2022-05-13 cs.CV cs.AI 57%

READ: Large-Scale Neural Scene Rendering for Autonomous Driving

Zhuopeng Li, Lu Li, Zeyu Ma, Ping Zhang, Junbo Chen, Jianke Zhu

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

2205.04334 2022-05-10 cs.CV 57%

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas Guibas, Andrea Tagliasacchi, Frank Dellaert, Thomas Funkhouser

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

Comments CVPR 2022 paper. See project page at https://abhijitkundu.info/projects/pnf

2203.09494 2022-05-10 cs.CV cs.LG 57%

Transframer: Arbitrary Frame Prediction with Generative Models

Charlie Nash, João Carreira, Jacob Walker, Iain Barr, Andrew Jaegle, Mateusz Malinowski, Peter Battaglia

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

2204.13696 2022-04-29 cs.CV 57%

NeurMiPs: Neural Mixture of Planar Experts for View Synthesis

Zhi-Hao Lin, Wei-Chiu Ma, Hao-Yu Hsu, Yu-Chiang Frank Wang, Shenlong Wang

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

Comments CVPR 2022. Project page: https://zhihao-lin.github.io/neurmips/

2204.00156 2022-04-04 cs.CV 57%

Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis

Qi Zhang, Xin Huang, Ying Feng, Xue Wang, Hongdong Li, Qing Wang

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

2112.09687 2022-03-30 cs.CV 57%

Light Field Neural Rendering

Mohammed Suhail, Carlos Esteves, Leonid Sigal, Ameesh Makadia

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

Comments Project page with code and videos at https://light-field-neural-rendering.github.io

1. 新视角合成 733 篇

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation

Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream

Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations

Consistent View Synthesis with Pose-Guided Diffusion Models

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views

Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes

Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image

Content-aware Warping for View Synthesis

Unsupervised Volumetric Animation

SparsePose: Sparse-View Camera Pose Regression and Refinement

High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Object Scene Representation Transformer

Floorplan-Aware Camera Poses Refinement

Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning

RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments

Video Extrapolation in Space and Time

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

RigNeRF: Fully Controllable Neural 3D Portraits

FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending

READ: Large-Scale Neural Scene Rendering for Autonomous Driving

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Transframer: Arbitrary Frame Prediction with Generative Models

NeurMiPs: Neural Mixture of Planar Experts for View Synthesis

Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis

Light Field Neural Rendering