3D Gaussian Splatting Papers

📢 改版公告 / Update Notice

由于论文数量激增，页面变得过长。为方便查阅，我们将2024年6月之前的论文暂时📁 归档（后续进一步整理），并把最新论文调整为按时间倒序排列。

Due to the rapid increase in the number of papers, the page has become too long. To facilitate the review, we have temporarily 📁 archived papers before Jan 2024 (which will be further organized) and rearranged latest papers in reverse chronological order.

📚 会议期刊:

• [ICLR2024] (2 篇) [3DV2024] (1 篇) [CVPR2024] (62 篇) [WACV2024] (1 篇) [ICML2024] (2 篇)
• [SIGGRAPH2024] (5 篇) [IJCAI2024] (1 篇) [ECCV2024]

📂 归档论文: [Before 2024/06/01] (285 篇)

---

[S0] A Survey on 3D Gaussian Splatting

• 🧑‍🔬 作者：Guikun Chen, Wenguan Wang
• 🏫 单位：Zhejiang University
• 🔗 链接：[中英摘要] [arXiv:2401.03890]
• 📝 说明：🔥 首篇综述

[S1] 3D Gaussian as a New Vision Era: A Survey

• 🧑‍🔬 作者：Ben Fei, Jingyi Xu, Rui Zhang, Qingyuan Zhou, Weidong Yang, Ying He
• 🏫 单位：Fudan University ⟐ Nanyang Technological University
• 🔗 链接：[中英摘要] [arXiv:2402.07181]
• 📝 说明：👍 相对比较全面，推荐精读

[S2] Recent Advances in 3D Gaussian Splatting

• 🧑‍🔬 作者：Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang, Yan-Pei Cao, Ling-Qi Yan, Lin Gao
• 🏫 单位：Chinese Academy of Sciences ⟐ VAST ⟐ University of California
• 🔗 链接：[中英摘要] [arXiv:2403.11134]
• 📝 说明：🔥 第三篇综述，涵盖了更多最新进展

[S3] Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review

• 🧑‍🔬 作者：Anurag Dalal, Daniel Hagen, Kjell G. Robbersmyr, Kristian Muri Knausgård
• 🏫 单位：University of Agder
• 🔗 链接：[中英摘要] [arXiv:2405.03417]
• 📝 说明：🔥 第四篇综述

---

[1] Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

• 🧑‍🔬 作者：Stanislaw Szymanowicz, Eldar Insafutdinov, Chuanxia Zheng, Dylan Campbell, João F. Henriques, Christian Rupprecht, Andrea Vedaldi
• 🏫 单位：VGG, University of Oxford ⟐ Australian National University
• 🔗 链接：[中英摘要] [arXiv:2406.04343] [Code]
• 📝 说明：

[2] Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

• 🧑‍🔬 作者：Fangfu Liu, Hanyang Wang, Shunyu Yao, Shengjun Zhang, Jie Zhou, Yueqi Duan
• 🏫 单位：Tsinghua University ⟐ Stanford University
• 🔗 链接：[中英摘要] [arXiv:2406.04338] [Code]
• 📝 说明：

[3] Localized Gaussian Point Management

• 🧑‍🔬 作者：Haosen Yang, Chenhao Zhang, Wenqing Wang, Marco Volino, Adrian Hilton, Li Zhang, Xiatian Zhu
• 🏫 单位：University of Surrey ⟐ Fudan University
• 🔗 链接：[中英摘要] [arXiv:2406.04251] [Code]
• 📝 说明：

[4] Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction

• 🧑‍🔬 作者：Diwen Wan, Ruijie Lu, Gang Zeng
• 🏫 单位：Peking University
• 🔗 链接：[中英摘要] [arXiv:2406.03697] [Code]
• 📝 说明：🏆 Accepted to ICML 2024

[5] Gaussian Representation for Deformable Image Registration

• 🧑‍🔬 作者：Jihe Li, Fabian Zhang, Xia Li, Tianhao Zhang, Ye Zhang, Joachim Buhmann
• 🏫 单位：Peking University ⟐ ETH Zurich ⟐ Tsinghua University ⟐ Paul Scherrer Institut
• 🔗 链接：[中英摘要] [arXiv:2406.03394] [Code]
• 📝 说明：

[6] Dynamic 3D Gaussian Fields for Urban Areas

• 🧑‍🔬 作者：Tobias Fischer, Jonas Kulhanek, Samuel Rota Bulò, Lorenzo Porzi, Marc Pollefeys, Peter Kontschieder
• 🏫 单位：ETH Zürich ⟐ Meta Reality Labs ⟐ CTU Prague
• 🔗 链接：[中英摘要] [arXiv:2406.03175] [Code]
• 📝 说明：

[7] Event3DGS: Event-based 3D Gaussian Splatting for Fast Egomotion

• 🧑‍🔬 作者：Tianyi Xiong, Jiayi Wu, Botao He, Cornelia Fermuller, Yiannis Aloimonos, Heng Huang, Christopher A. Metzler
• 🏫 单位：University of Maryland, College Park
• 🔗 链接：[中英摘要] [arXiv:2406.02972] [Code]
• 📝 说明：

[8] Adversarial Generation of Hierarchical Gaussians for 3D Generative Model

• 🧑‍🔬 作者：Sangeek Hyun, Jae-Pil Heo
• 🏫 单位：Sungkyunkwan University
• 🔗 链接：[中英摘要] [arXiv:2406.02968] [Code]
• 📝 说明：

[9] 3D-HGS: 3D Half-Gaussian Splatting

• 🧑‍🔬 作者：Haolin Li, Jinyang Liu, Mario Sznaier, Octavia Camps
• 🏫 单位：Northeastern University
• 🔗 链接：[中英摘要] [arXiv:2406.02720] [Code]
• 📝 说明：

[10] Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

• 🧑‍🔬 作者：Inkyu Shin, Qihang Yu, Xiaohui Shen, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
• 🏫 单位：KAIST ⟐ ByteDance
• 🔗 链接：[中英摘要] [arXiv:2406.02541] [Code]
• 📝 说明：

[11] SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition

• 🧑‍🔬 作者：Van Minh Nguyen, Emma Sandidge, Trupti Mahendrakar, Ryan T. White
• 🏫 单位：NEural TransmissionS (NETS) Lab Florida Institute of Technology
• 🔗 链接：[中英摘要] [arXiv:2406.02533] [Code]
• 📝 说明：

[12] DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering

• 🧑‍🔬 作者：Zhongpai Gao, Benjamin Planche, Meng Zheng, Xiao Chen, Terrence Chen, Ziyan Wu
• 🏫 单位：United Imaging Intelligence, Boston, MA
• 🔗 链接：[中英摘要] [arXiv:2406.02518] [Code]
• 📝 说明：

[13] WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections

• 🧑‍🔬 作者：Yuze Wang, Junyi Wang, Yue Qi
• 🏫 单位：Beihang University
• 🔗 链接：[中英摘要] [arXiv:2406.02407] [Code]
• 📝 说明：

[14] Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning

• 🧑‍🔬 作者：Jiaxu Wang, Ziyi Zhang, Qiang Zhang, Jia Li, Jingkai Sun, Mingyuan Sun, Junhao He, Renjing Xu
• 🏫 单位：HKUST (GZ) ⟐ HKU ⟐ NEU
• 🔗 链接：[中英摘要] [arXiv:2406.02370] [Code]
• 📝 说明：

[15] OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

• 🧑‍🔬 作者：Yanmin Wu, Jiarui Meng, Haijie Li, Chenming Wu, Yahao Shi, Xinhua Cheng, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Jian Zhang
• 🏫 单位：Peking University ⟐ Baidu VIS ⟐ Beihang University
• 🔗 链接：[中英摘要] [arXiv:2406.02058] [Code]
• 📝 说明：

[16] FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping

• 🧑‍🔬 作者：Yuzhou Ji, He Zhu, Junshu Tang, Wuyi Liu, Zhizhong Zhang, Yuan Xie, Lizhuang Ma, Xin Tan
• 🏫 单位：East China Normal University ⟐ Shanghai Jiao Tong University
• 🔗 链接：[中英摘要] [arXiv:2406.01916] [Code]
• 📝 说明：

[17] End-to-End Rate-Distortion Optimized 3D Gaussian Representation

• 🧑‍🔬 作者：Henan Wang, Hanxin Zhu, Tianyu He, Runsen Feng, Jiajun Deng, Jiang Bian, Zhibo Chen
• 🏫 单位：University of Science and Technology of China ⟐ Microsoft Research Asia ⟐ The University of Adelaide
• 🔗 链接：[中英摘要] [arXiv:2406.01597] [Code]
• 📝 说明：

[18] Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting

• 🧑‍🔬 作者：Shaojie Ma, Yawei Luo, Yi Yang
• 🏫 单位：Zhejiang University
• 🔗 链接：[中英摘要] [arXiv:2406.01593] [Code]
• 📝 说明：

[19] Tetrahedron Splatting for 3D Generation

• 🧑‍🔬 作者：Chun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang
• 🏫 单位：Fudan University ⟐ University of Surrey
• 🔗 链接：[中英摘要] [arXiv:2406.01579] [Code]
• 📝 说明：

[20] DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians with Video Diffusion Priors

• 🧑‍🔬 作者：Tianyu Huang, Yihan Zeng, Hui Li, Wangmeng Zuo, Rynson W. H. Lau
• 🏫 单位：City University of Hong Kong ⟐ Harbin Institute of Technology ⟐ Huawei Noah’s Ark Lab
• 🔗 链接：[中英摘要] [arXiv:2406.01476] [Code]
• 📝 说明：

[21] RaDe-GS: Rasterizing Depth in Gaussian Splatting

• 🧑‍🔬 作者：Baowen Zhang, Chuan Fang, Rakesh Shrestha, Yixun Liang, Xiaoxiao Long, Ping Tan
• 🏫 单位：Hong Kong University of Science and Technology ⟐ Simon Fraser University
• 🔗 链接：[中英摘要] [arXiv:2406.01467] [Code]
• 📝 说明：

[22] Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting

• 🧑‍🔬 作者：Fang Li, Hao Zhang, Narendra Ahuja
• 🏫 单位：University of Illinois at Urbana-Champaign
• 🔗 链接：[中英摘要] [arXiv:2406.01042] [Code]
• 📝 说明：

[23] SuperGaussian: Repurposing Video Models for 3D Super Resolution

• 🧑‍🔬 作者：Yuan Shen, Duygu Ceylan, Paul Guerrero, Zexiang Xu, Niloy J. Mitra, Shenlong Wang, Anna Früstück
• 🏫 单位：University of Illinois at Urbana-Champaign ⟐ Adobe Research ⟐ University College London
• 🔗 链接：[中英摘要] [arXiv:2406.00609] [Code]
• 📝 说明：

[24] Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture

• 🧑‍🔬 作者：X. Li, Y. Cheng, X. Ren, H. Jia, D. Xu, W. Zhu, Y. Yan
• 🏫 单位：Shanghai Jiao Tong University ⟐ Huawei Cloud Computing Technologies Co., Ltd
• 🔗 链接：[中英摘要] [arXiv:2406.00440] [Code]
• 📝 说明：

[25] MoDGS: Dynamic Gaussian Splatting from Causually-captured Monocular Videos

• 🧑‍🔬 作者：Qingming Liu, Yuan Liu, Jiepeng Wang, Xianqiang Lv, Peng Wang, Wenping Wang, Junhui Hou
• 🏫 单位：City University of Hong kong ⟐ The University of Hong kong ⟐ Texas A&M University, U.S.A
• 🔗 链接：[中英摘要] [arXiv:2406.00434] [Code]
• 📝 说明：