3D 视觉

CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

Yang Liu, He Guan, Chuanchen Luo, Lue Fan, Naiyan Wang, Junran Peng, Zhaoxiang Zhang

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

Comments Accepted by ECCV2024; Project Page: https://dekuliutesla.github.io/citygs/

EscherNet: A Generative Model for Scalable View Synthesis

Xin Kong, Shikun Liu, Xiaoyang Lyu, Marwan Taher, Xiaojuan Qi, Andrew J. Davison

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

Comments CVPR2024 Project Page: https://kxhit.github.io/EscherNet

PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation

Yuhan Ding, Fukun Yin, Jiayuan Fan, Hui Li, Xin Chen, Wen Liu, Chongshan Lu, Gang YU, Tao Chen

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

Comments Accepted to NeurIPS 2023

HexPlane: A Fast Representation for Dynamic Scenes

Ang Cao, Justin Johnson

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

Comments CVPR 2023, Camera Ready Project page: https://caoang327.github.io/HexPlane

3D GAN Inversion with Pose Optimization

Jaehoon Ko, Kyusun Cho, Daewon Choi, Kwangrok Ryoo, Seungryong Kim

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

Comments Project Page: https://3dgan-inversion.github.io

Systematic Evaluation of Novel View Synthesis for Video Place Recognition

面向视频地点识别的合成新视角系统性评估

Muhammad Zawad Mahmud, Samiha Islam, Damian Lyons

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

AI总结 系统评估合成新视角对视频地点识别的影响，发现少量合成视角可提升识别性能，且视角变化幅度不如添加数量和图像类型重要。

Comments Submitted to IEEE IROS 2026

altiro3D: Scene representation from single image and novel view synthesis

altiro3D: 从单张图像和新视角合成生成场景表示

E. Canessa, L. Tenze

机构 * The Abdus Salam International Centre for Theoretical Physics, ICTP, Trieste 34151, Italy（阿布杜斯·萨拉姆国际理论物理学中心，ICTP，特里埃斯特） 纠错

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

AI总结 altiro3D通过单张图像生成多视角和视频，结合深度估计与快速算法实现逼真3D体验。

Comments In press (2023) Springer International Journal of Information Technology (IJIT) 10 pages, 3 figures

Journal ref International Journal of Information Technology 16 (2024) 33

SVS: Adversarial refinement for sparse novel view synthesis

Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson, Stephen Jolly, Simon Hadfield

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

Comments BMVC 2022

Self-improving Multiplane-to-layer Images for Novel View Synthesis

Pavel Solovev, Taras Khakhulin, Denis Korzhenkov

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

Comments Accepted for WACV 2023

Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis

学习光谱和偏振线索用于一对多模态新视角合成

Federico Lincetto, Gianluca Agresti, Mattia Rossi, Piergiorgio Sartor, Pietro Zanuttigh

机构 * MEDIA Lab（媒体实验室） ； University of Padova（帕多瓦大学） ； Sony EUISPC（索尼欧洲影像处理中心） ； Sony Semiconductor Solutions Europe（索尼半导体解决方案欧洲分公司） 纠错

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

AI总结 提出SPoILeR方法，通过多模态预训练学习模态间相关性，在仅RGB监督下实现未见场景的多模态新视角渲染。

Comments Accepted at ECCV 2026. Project page: https://medialab.dei.unipd.it/paper_data/SPoILeR/

CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy

CD-RCM：面向反射共聚焦显微镜的泛化连续深度新视角合成

Tooba Imtiaz, Milind Rajadhyaksha, Kivanc Kose, Jennifer Dy

机构 * Northeastern University（东北大学） ； Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心） 纠错

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

AI总结 针对反射共聚焦显微镜各向异性3D体积，提出首个RCM专用新视角合成方法CD-RCM，通过前馈模型从稀疏z-stack预测连续深度切片，实现亚秒级高保真合成。

3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark

3DAE: 基于空间图谱和基准的音频新视角合成双耳质量评估

Jialu Xu, Yifan Zhou

机构 * University of Waterloo（滑铁卢大学） 纠错

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

AI总结 提出一个全参考诊断框架3DAE Map，通过时频音频误差图（幅度、ILD、IPD、时间对齐、响度和高频故障）进行视觉检查，并构建模型无关基准3DAE Bench，用于评估音频新视角合成模型的双耳预测质量。

RAVEN: Erasing Invisible Watermarks via Novel View Synthesis

RAVEN：通过新颖的视角合成消除不可见水印

Fahad Shamshad, Nils Lukas, Karthik Nandakumar

机构 * MBZUAI, UAE（阿联酋MBZUAI） ； Michigan State University, USA（美国密歇根州立大学） 纠错

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

AI总结 RAVEN通过新颖的视角合成方法，在不依赖检测器或水印知识的情况下，实现了对多种水印方案的高效抑制，提升了水印去除的鲁棒性。

Comments 13 pages

Novel View Synthesis using DDIM Inversion

基于DDIM反向的新型视图合成

Sehajdeep Singh, A V Subramanyam, Aditya Gupta, Sahil Gupta

机构 * Indraprastha Institute of Information Technology（印度普拉斯塔大学信息科技学院） 纠错

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

AI总结 本文提出基于DDIM反向的轻量级视图合成方法，利用预训练扩散模型生成高质量新视角重建。

RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis

Hugo Blanc, Jean-Emmanuel Deschaud, Alexis Paljic

机构 * Mines Paris, PSL University, Centre for robotics（巴黎 Mines 学院、PSL 大学、机器人中心） 纠错

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

Comments Project page with videos and code: https://raygaussx.github.io/

RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation

Henrique Piñeiro Monteagudo, Leonardo Taccari, Aurel Pjetri, Francesco Sambo, Samuele Salti

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

Comments Accepted at WACV 2025

Journal ref 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 2025, pp. 535-544

CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation

Alex Berian, Daniel Brignac, JhihYang Wu, Natnael Daba, Abhijit Mahalanobis

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

Comments Accepted in the 2025 WACV workshop GeoCV

Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering

Ido Sobol, Chenfeng Xu, Or Litany

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

Comments NeurIPS 2024. Project page: https://zero2hero-nvs.github.io

Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering

Francesco Di Sario, Riccardo Renzulli, Enzo Tartaglione, Marco Grangetto

专题命中 新视角合成 ：NeRF(title)；分类 cs.CV

Comments The paper has been accepted to the ECCV 2024 conference

Baking Relightable NeRF for Real-time Direct/Indirect Illumination Rendering

Euntae Choi, Vincent Carpentier, Seunghun Shin, Sungjoo Yoo

专题命中 新视角合成 ：NeRF(title)；分类 cs.CV

Comments Under review

Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis

Jianning Deng, Kartic Subr, Hakan Bilen

专题命中 新视角合成 ：NeRF(title)；分类 cs.CV

Comments 9 pages for the maincontent, excluding references and supplementaries

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis

Zinuo You, Andreas Geiger, Anpei Chen

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

Comments CVPR 2024 Conference Paper, Camera Ready Version

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

Tianshu Huang, John Miller, Akarsh Prabhakara, Tao Jin, Tarana Laroia, Zico Kolter, Anthony Rowe

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

Comments To appear in CVPR 2024; see https://wiselabcmu.github.io/dart/ for our project site

Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes

Haotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, Xiaowei Zhou

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

Comments SIGGRAPH Asia 2023; Project page: https://zju3dv.github.io/im4d

Geometry-biased Transformers for Novel View Synthesis

Naveen Venkat, Mayank Agarwal, Maneesh Singh, Shubham Tulsiani

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

Comments Project page: https://mayankgrwl97.github.io/gbt

Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis

Wei Cheng, Su Xu, Jingtan Piao, Chen Qian, Wayne Wu, Kwan-Yee Lin, Hongsheng Li

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

Comments Project Page: https://generalizable-neural-performer.github.io/ Dataset: https://generalizable-neural-performer.github.io/genebody.html/

Novel View Synthesis from a Single Image via Unsupervised learning

Bingzheng Liu, Jianjun Lei, Bo Peng, Chuanbo Yu, Wanqing Li, Nam Ling

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

Comments 9 pages, submitted to TCSVT

Deep Learning based Novel View Synthesis

Amit More, Subhasis Chaudhuri

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

Layout-Guided Novel View Synthesis from a Single Indoor Panorama

Jiale Xu, Jia Zheng, Yanyu Xu, Rui Tang, Shenghua Gao

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

Comments To appear in CVPR 2021

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

IVGT：隐式视觉几何变换器用于神经场景表示

Yuqi Wu, Tianyu Hu, Wenzhao Zheng, Yuanhui Huang, Haowen Sun, Jie Zhou, Jiwen Lu

机构 * Intelligent Vision Group, Tsinghua University（清华大学智能视觉组） 纠错

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

AI总结 本文提出IVGT，一种隐式视觉几何变换器，通过无姿态多视角图像隐式建模连续且一致的几何结构，从而实现神经场景表示，支持在任意3D位置进行连续空间查询，以预测签名距离和颜色，并在多个任务中表现出色。

Comments Code: https://github.com/wzzheng/IVGT/