3D 视觉 - arXivDaily 专题

2205.15595 2022-06-01 cs.CV 79%

Novel View Synthesis for High-fidelity Headshot Scenes

Satoshi Tsutsui, Weijia Mao, Sijing Lin, Yunyi Zhu, Murong Ma, Mike Zheng Shou

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

2204.03476 2022-04-08 cs.CV 79%

ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling

Yuemei Zhou, Tao Yu, Zerong Zheng, Ying Fu, Yebin Liu

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

2111.12731 2022-02-22 cs.CV 79%

Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

Guillaume Rochette, Chris Russell, Richard Bowden

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

Comments Accepted at Face and Gesture 2021, 8 pages, 7 figures

2102.03285 2021-12-16 cs.CV 79%

Unsupervised Novel View Synthesis from a Single Image

Pierluigi Zama Ramirez, Diego Martin Arroyo, Alessio Tonioni, Federico Tombari

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

Comments Submitted to Computer Vision and Image Understanding (CVIU)

2105.05994 2021-05-14 cs.CV 79%

Neural Trajectory Fields for Dynamic Novel View Synthesis

Chaoyang Wang, Ben Eckart, Simon Lucey, Orazio Gallo

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

2103.15407 2021-04-06 cs.CV 79%

Self-Supervised Visibility Learning for Novel View Synthesis

Yujiao Shi, Hongdong Li, Xin Yu

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

Comments accepted to CVPR2021

2012.15838 2021-03-30 cs.CV 79%

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou

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

Comments CVPR 2021. Project page: https://zju3dv.github.io/neuralbody/

2101.01619 2021-01-06 cs.CV 79%

Novel View Synthesis via Depth-guided Skip Connections

Yuxin Hou, Arno Solin, Juho Kannala

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

2010.11468 2020-10-23 cs.CV 79%

Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks

Xiang Guo, Bo Li, Yuchao Dai, Tongxin Zhang, Hui Deng

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

Comments Accepted by International Conference on Pattern Recognition (ICPR 2020)

2007.10618 2020-07-22 cs.CV 79%

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

Mingyu Yin, Li Sun, Qingli Li

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

Comments ECCV 2020

2004.01294 2020-04-06 cs.CV 79%

Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera

Jae Shin Yoon, Kihwan Kim, Orazio Gallo, Hyun Soo Park, Jan Kautz

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

Comments This paper is accepted to CVPR 2020

1909.12224 2019-10-02 cs.CV cs.LG eess.IV 79%

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

Wen Liu, Zhixin Piao, Jie Min, Wenhan Luo, Lin Ma, Shenghua Gao

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

Comments accepted by ICCV2019

1808.08688 2018-08-28 cs.CV 79%

Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis

Xibin Song, Yuchao Dai, Xueying Qin

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

Comments Accepted by IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT) 2018

1804.06008 2018-04-18 cs.CV 79%

Geometry-aware Deep Network for Single-Image Novel View Synthesis

Miaomiao Liu, Xuming He, Mathieu Salzmann

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

Comments CVPR 2018

1802.07064 2018-02-21 cs.CV 79%

Novel View Synthesis for Large-scale Scene using Adversarial Loss

Xiaochuan Yin, Henglai Wei, Penghong lin, Xiangwei Wang, Qijun Chen

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

2511.20620 2026-03-30 cs.CV cs.RO 79%

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

Wanderland: 为开放世界具身AI提供几何学基础的模拟

Xinhao Liu, Jiaqi Li, Youming Deng, Ruxin Chen, Yingjia Zhang, Yifei Ma, Li Guo, Yiming Li, Jing Zhang, Chen Feng

机构 * New York University（纽约大学）； Cornell University（康奈尔大学）

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

AI总结本文提出Wanderland框架，通过多传感器采集和高精度几何重建，解决开放世界具身AI中模拟与现实差距大的问题，并展示其在导航政策学习中的应用。

Comments CVPR 2026

2504.03415 2025-04-07 cs.GR cs.CV cs.LG cs.MM cs.PF 79%

NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devices

Zhe Wang, Yifei Zhu

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

Comments This paper is accepted by 45th IEEE International Conference on Distributed Computing Systems (ICDCS 2025)

2410.17242 2025-04-04 cs.CV cs.GR cs.LG 79%

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Sai Bi, Tianyuan Zhang, Fujun Luan, Noah Snavely, Zexiang Xu

专题命中新视角合成：NeRF(abstract)；3DGS(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments project page: https://haian-jin.github.io/projects/LVSM/

2205.14330 2023-07-06 cs.CV cs.GR 79%

Differentiable Point-Based Radiance Fields for Efficient View Synthesis

Qiang Zhang, Seung-Hwan Baek, Szymon Rusinkiewicz, Felix Heide

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

2303.17094 2023-03-31 cs.CV cs.GR 79%

Enhanced Stable View Synthesis

Nishant Jain, Suryansh Kumar, Luc Van Gool

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

Comments Accepted to IEEE/CVF CVPR 2023. Draft info: 13 pages, 6 Figures, 7 Tables

2111.13152 2022-03-30 cs.CV cs.AI cs.GR cs.LG cs.RO 78%

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi

专题命中新视角合成：novel view synthesis(title)；分类 cs.CV、cs.GR、cs.RO

Comments Accepted to CVPR 2022, Project website: https://srt-paper.github.io/

Journal ref CVPR 2022

2603.23413 2026-08-03 cs.CV 版本更新 77%

I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation

I3DM：隐式3D-aware记忆检索与注入用于一致的视频场景生成

Jia Li, Han Yan, Yihang Chen, Siqi Li, Xibin Song, Yifu Wang, Jianfei Cai, Tien-Tsin Wong, Pan Ji

机构 * Monash University（莫纳什大学）； Vertex Lab（Vertex实验室）； Shanghai Jiao Tong University（上海交通大学）

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

AI总结本文提出I3DM，一种隐式3D-aware记忆机制，通过预训练FF-NVS模型的中间特征进行视图相关性评分，提升复杂遮挡下的场景一致性生成效果。

Comments Project page: https://riga2.github.io/i3dm

2604.01761 2026-07-03 cs.CV 版本更新 77%

Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion

Control-DINO：用于可控图像到视频扩散的特征空间条件

Edoardo A. Dominici, Thomas Deixelberger, Konstantinos Vardis, Markus Steinberger

机构 * Huawei Technologies, Switzerland（华为技术（瑞士））； Huawei Technologies, Austria（华为技术（奥地利））； Graz University of Technology, Austria（格拉茨技术大学）

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

AI总结本文提出Control-DINO，通过解耦外观与其他特征，实现对视频扩散模型的可控生成，提升生成渲染的可控性。

Comments ECCV 2026 - Project Page https://dedoardo.github.io/projects/control-dino/

2606.31258 2026-07-01 cs.CV 新提交 77%

WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis

WarpHammer: 利用3D物体先验稠密化场景扭曲以实现极端视角合成

Michael Green, Gavriel Habib, Dvir Samuel, Tal Berkovitz Shalev, Issar Tzachor, Rami Ben-Ari, Or Litany

机构 * OriginAI, Israel（OriginAI，以色列）； NVIDIA（英伟达）； Technion（以色列理工学院）

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

AI总结针对投影条件新视角合成在大轨道运动下扭曲稀疏导致生成失败的问题，提出无需训练的WarpHammer框架，通过引入3D生成先验的物体显式重建来补充缺失前景并遮挡不应可见的背景点，恢复外观和相机线索，并首次支持融合外部辅助物体视图。

2603.08133 2026-03-10 cs.CV 77%

Fast Low-light Enhancement and Deblurring for 3D Dark Scenes

快速低光照增强与去模糊用于3D暗场景

Feng Zhang, Jinglong Wang, Ze Li, Yanghong Zhou, Yang Chen, Lei Chen, Xiatian Zhu

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

AI总结 FLED-GS通过交替增强和重建循环，实现快速低光照和运动模糊图像的3D场景恢复，优于现有方法，训练和渲染速度提升显著。

Comments 5 pages, 2 figures, Accepted at ICASSP 2026

2504.13339 2026-01-14 cs.GR 77%

Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering

体积编码高斯：用于体积渲染的无转移函数依赖的3D高斯

Landon Dyken, Andres Sewell, Will Usher, Nathan Debardeleben, Steve Petruzza, Sidharth Kumar

专题命中新视角合成：Gaussian Splatting(abstract)；3DGS(abstract)；novel view synthesis(abstract)；分类 cs.GR

AI总结提出体积编码高斯方法，通过无转移函数依赖的3D高斯表示实现高效体积渲染，优于现有方法并节省资源。

2512.14406 2025-12-17 cs.CV 77%

Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos

从受限单目视频中广义动态场景视图合成

Le Jiang, Shaotong Zhu, Yedi Luo, Shayda Moezzi, Sarah Ostadabbas

机构 * Northeastern University（东北大学）

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

AI总结 ExpanDyNeRF通过高斯溅射先验和伪地面真实生成策略，实现从受限单目视频中高质量动态场景视图合成，并在SynDM数据集上验证其在极端视角偏移下的优越性能。

2410.01804 2025-07-25 cs.CV 77%

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

Alexander Mai, Peter Hedman, George Kopanas, Dor Verbin, David Futschik, Qiangeng Xu, Falko Kuester, Jonathan T. Barron, Yinda Zhang

机构 * Google（谷歌）

专题命中新视角合成：NeRF(abstract)；Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV

Comments Project page: https://half-potato.gitlab.io/posts/ever

2503.24374 2025-04-01 cs.CV 77%

ERUPT: Efficient Rendering with Unposed Patch Transformer

Maxim V. Shugaev, Vincent Chen, Maxim Karrenbach, Kyle Ashley, Bridget Kennedy, Naresh P. Cuntoor

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

Comments Accepted to CVPR 2025

2503.18363 2025-04-01 cs.CV 77%

MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction

Wenyuan Zhang, Yixiao Yang, Han Huang, Liang Han, Kanle Shi, Yu-Shen Liu, Zhizhong Han

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

Comments Accepted by CVPR 2025. Project page: https://wen-yuan-zhang.github.io/MonoInstance/

1. 新视角合成 733 篇

Novel View Synthesis for High-fidelity Headshot Scenes

ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling

Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

Unsupervised Novel View Synthesis from a Single Image

Neural Trajectory Fields for Dynamic Novel View Synthesis

Self-Supervised Visibility Learning for Novel View Synthesis

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

Novel View Synthesis via Depth-guided Skip Connections

Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis

Geometry-aware Deep Network for Single-Image Novel View Synthesis

Novel View Synthesis for Large-scale Scene using Adversarial Loss

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devices

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

Differentiable Point-Based Radiance Fields for Efficient View Synthesis

Enhanced Stable View Synthesis

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation

Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion

WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis

Fast Low-light Enhancement and Deblurring for 3D Dark Scenes

Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering

Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

ERUPT: Efficient Rendering with Unposed Patch Transformer

MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction