3D 视觉 - arXivDaily 专题

2410.05468 2024-10-15 cs.CV 70%

PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis

Chuanhao Sun, Thanos Triantafyllou, Anthos Makris, Maja Drmač, Kai Xu, Luo Mai, Mahesh K. Marina

专题命中新视角合成：NeRF(abstract)；Gaussian Splatting(abstract)；分类 cs.CV

Comments 21 pages, in submision

2410.00672 2024-10-02 cs.CV 70%

GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer

Youngho Yoon, Hyun-Kurl Jang, Kuk-Jin Yoon

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

Comments Accepted at ECCV 2024. Code available at https://github.com/yh-yoon/GMT

2409.15041 2024-09-24 cs.CV 70%

AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark

Michal Nazarczuk, Thomas Tanay, Sibi Catley-Chandar, Richard Shaw, Radu Timofte, Eduardo Pérez-Pellitero

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

Comments Part of Advances in Image Manipulation workshop at ECCV 2024. Available at: https://sparebenchmark.github.io/

2301.01490 2024-09-20 cs.CV 70%

Towards a Pipeline for Real-Time Visualization of Faces for VR-based Telepresence and Live Broadcasting Utilizing Neural Rendering

Philipp Ladwig, Rene Ebertowski, Alexander Pech, Ralf Dörner, Christian Geiger

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

2408.16866 2024-09-02 cs.CV 70%

GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content

Lebin Zhou, Kun Han, Nam Ling, Wei Wang, Wei Jiang

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

2408.06592 2024-08-14 cs.CV 70%

ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection

Jianyu Tao, Changping Hu, Edward Yang, Jing Xu, Rui Chen

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

Comments 18 pages, 10 figures

2407.21450 2024-08-05 cs.CV 70%

Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

Sudhir Yarram, Junsong Yuan

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

Comments Accepted to ECCV 2024. Project Page: https://skrya.github.io/projects/ffn-dsr/

2401.12592 2024-07-30 cs.CV 70%

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

Hongchi Xia, Yang Fu, Sifei Liu, Xiaolong Wang

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

Comments Our project page: https://wildrgbd.github.io/

2309.07986 2024-07-29 cs.CV cs.AI cs.LG 70%

Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models

James Burgess, Kuan-Chieh Wang, Serena Yeung-Levy

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

Comments ECCV 2024 (European Conference on Computer Vision). Project page: https://jmhb0.github.io/view_neti/

2404.15259 2024-07-24 cs.CV 70%

FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent

Cameron Smith, David Charatan, Ayush Tewari, Vincent Sitzmann

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

Comments Project website: https://cameronosmith.github.io/flowmap/

2312.02135 2024-07-22 cs.CV 70%

Fast View Synthesis of Casual Videos with Soup-of-Planes

Yao-Chih Lee, Zhoutong Zhang, Kevin Blackburn-Matzen, Simon Niklaus, Jianming Zhang, Jia-Bin Huang, Feng Liu

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

Comments Accepted to ECCV 2024. Project page: https://casual-fvs.github.io/

2310.06744 2024-07-15 cs.CV 70%

HiFi-123: Towards High-fidelity One Image to 3D Content Generation

Wangbo Yu, Li Yuan, Yan-Pei Cao, Xiangjun Gao, Xiaoyu Li, Wenbo Hu, Long Quan, Ying Shan, Yonghong Tian

专题命中新视角合成：novel view synthesis(abstract)；3D generation(abstract)；分类 cs.CV

Comments Accepted by ECCV 2024. Project Page: https://drexubery.github.io/HiFi-123/

2407.02668 2024-07-04 cs.CV 70%

MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering

Ahmad AlMughrabi, Ricardo Marques, Petia Radeva

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

2310.10375 2024-06-10 cs.CV cs.AI cs.LG stat.ML 70%

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

Takeru Miyato, Bernhard Jaeger, Max Welling, Andreas Geiger

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

Comments Published as a conference paper at ICLR 2024

2406.00598 2024-06-04 cs.CV 70%

Efficient Neural Light Fields (ENeLF) for Mobile Devices

Austin Peng

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

2303.12786 2024-04-10 cs.CV 70%

FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

Jianglong Ye, Naiyan Wang, Xiaolong Wang

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

Comments Project page: https://jianglongye.com/featurenerf/

2404.03652 2024-04-05 cs.CV 70%

The More You See in 2D, the More You Perceive in 3D

Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman

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

Comments Project page: https://sap3d.github.io/

2403.06394 2024-03-14 cs.CV 70%

FSViewFusion: Few-Shots View Generation of Novel Objects

Rukhshanda Hussain, Hui Xian Grace Lim, Borchun Chen, Mubarak Shah, Ser Nam Lim

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

2403.06738 2024-03-12 cs.CV 70%

V3D: Video Diffusion Models are Effective 3D Generators

Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu

专题命中新视角合成：novel view synthesis(abstract)；3D generation(abstract)；分类 cs.CV

Comments Code available at https://github.com/heheyas/V3D Project page: https://heheyas.github.io/V3D/

2402.05235 2024-02-09 cs.CV 70%

SPAD : Spatially Aware Multiview Diffusers

Yash Kant, Ziyi Wu, Michael Vasilkovsky, Guocheng Qian, Jian Ren, Riza Alp Guler, Bernard Ghanem, Sergey Tulyakov, Igor Gilitschenski, Aliaksandr Siarohin

专题命中新视角合成：novel view synthesis(abstract)；3D generation(abstract)；分类 cs.CV

Comments Webpage: https://yashkant.github.io/spad

2401.05583 2024-01-12 cs.CV 70%

Diffusion Priors for Dynamic View Synthesis from Monocular Videos

Chaoyang Wang, Peiye Zhuang, Aliaksandr Siarohin, Junli Cao, Guocheng Qian, Hsin-Ying Lee, Sergey Tulyakov

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

2211.14108 2023-10-13 cs.CV 70%

3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models

Gang Li, Heliang Zheng, Chaoyue Wang, Chang Li, Changwen Zheng, Dacheng Tao

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

Comments Submitted to IJCV

2309.11627 2023-09-22 cs.CV 70%

GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis

Youssef Abdelkareem, Shady Shehata, Fakhri Karray

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

Comments Accepted to GCPR 2023

2308.11198 2023-08-23 cs.CV 70%

Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views

Wentian Qu, Zhaopeng Cui, Yinda Zhang, Chenyu Meng, Cuixia Ma, Xiaoming Deng, Hongan Wang

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

2307.05663 2023-07-13 cs.CV cs.AI 70%

Objaverse-XL: A Universe of 10M+ 3D Objects

Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, Ali Farhadi

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

2212.08057 2023-06-27 cs.CV cs.AI cs.LG 70%

Real-Time Neural Light Field on Mobile Devices

Junli Cao, Huan Wang, Pavlo Chemerys, Vladislav Shakhrai, Ju Hu, Yun Fu, Denys Makoviichuk, Sergey Tulyakov, Jian Ren

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

Comments CVPR 2023. Project page: https://snap-research.github.io/MobileR2L/ Code: https://github.com/snap-research/MobileR2L/

2304.14401 2023-04-28 cs.CV 70%

ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs

Jiteng Mu, Shen Sang, Nuno Vasconcelos, Xiaolong Wang

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

Comments Project Page : https://jitengmu.github.io/ActorsNeRF/

2304.09527 2023-04-21 cs.CV 70%

Single-View View Synthesis with Self-Rectified Pseudo-Stereo

Yang Zhou, Hanjie Wu, Wenxi Liu, Zheng Xiong, Jing Qin, Shengfeng He

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

2304.06969 2023-04-17 cs.CV 70%

UVA: Towards Unified Volumetric Avatar for View Synthesis, Pose rendering, Geometry and Texture Editing

Jinlong Fan, Jing Zhang, Dacheng Tao

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

2304.03266 2023-04-07 cs.CV 70%

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

Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, Sanja Fidler

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

Comments CVPR 2023. Project page: https://nv-tlabs.github.io/fegr/

1. 新视角合成 733 篇

PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis

GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer

AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark

Towards a Pipeline for Real-Time Visualization of Faces for VR-based Telepresence and Live Broadcasting Utilizing Neural Rendering

GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content

ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection

Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models

FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent

Fast View Synthesis of Casual Videos with Soup-of-Planes

HiFi-123: Towards High-fidelity One Image to 3D Content Generation

MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

Efficient Neural Light Fields (ENeLF) for Mobile Devices

FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

The More You See in 2D, the More You Perceive in 3D

FSViewFusion: Few-Shots View Generation of Novel Objects

V3D: Video Diffusion Models are Effective 3D Generators

SPAD : Spatially Aware Multiview Diffusers

Diffusion Priors for Dynamic View Synthesis from Monocular Videos

3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models

GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis

Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views

Objaverse-XL: A Universe of 10M+ 3D Objects

Real-Time Neural Light Field on Mobile Devices

ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs

Single-View View Synthesis with Self-Rectified Pseudo-Stereo

UVA: Towards Unified Volumetric Avatar for View Synthesis, Pose rendering, Geometry and Texture Editing

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