Point'n Move: Interactive scene object manipulation on Gaussian splatting radiance fields

被引:0
|
作者
Huang, Jiajun [1 ]
Yu, Hongchuan [1 ]
Zhang, Jianjun [1 ]
Nait-Charif, Hammadi [1 ]
机构
[1] Natl Ctr Comp Animat, Poole BH12 5BB, Dorset, England
基金
英国工程与自然科学研究理事会;
关键词
computer animation; computer graphics; computer vision;
D O I
10.1049/ipr2.13190
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The authors propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real-time editing. To achieve this, Gaussian Splatting Radiance Field is adopted as the scene representation and its explicit nature and speed advantage are fully leveraged. Its explicit representation formulation allows to devise a 2D prompt points to 3D masks dual-stage self-prompting segmentation algorithm, perform mask refinement and merging, minimize changes, and provide good initialization for scene inpainting and perform editing in real-time without per-editing training; all lead to superior quality and performance. The method was tested by editing both forward-facing and 360 scenes. The method is also compared against existing methods, showing superior quality despite being more capable and having a speed advantage. We propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here refers to intuitive object selection and real-time editing. This is achieved by devising a pipeline that fully exploits the explicit nature of our adopted scene representation. Our method achieves superior quality against existing object removal methods despite being more capable and having a speed advantage. image
引用
收藏
页码:3507 / 3517
页数:11
相关论文
共 14 条
  • [1] EGGS: Edge Guided Gaussian Splatting for Radiance Fields
    Gong, Yuanhao
    29TH INTERNATIONAL ACM CONFERENCE ON 3D WEB TECHNOLOGY, WEB3D 2024, 2024,
  • [2] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
    Huang, Binbin
    Yu, Zehao
    Chen, Anpei
    Geiger, Andreas
    Gao, Shenghua
    PROCEEDINGS OF SIGGRAPH 2024 CONFERENCE PAPERS, 2024,
  • [3] Scene-Generalizable Interactive Segmentation of Radiance Fields
    Tang, Songlin
    Pei, Wenjie
    Tao, Xin
    Jia, Tanghui
    Lu, Guangming
    Tai, Yu-Wing
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 6744 - 6755
  • [4] Illuminating the Moon: Reconstruction of lunar terrain using photogrammetry, Neural Radiance Fields, and Gaussian Splatting
    Prosvetov, A.
    Govorov, A.
    Pupkov, M.
    Andreev, A.
    Nazarov, V.
    ASTRONOMY AND COMPUTING, 2025, 52
  • [5] GaussMR: Interactive Gaussian Splatting Sandbox with GPU Particles and Signed Distance Fields
    Taniguchi, Daiki
    PROCEEDINGS OF THE SIGGRAPH 2024 IMMERSIVE PAVILION, 2024,
  • [6] Integration of 3D Gaussian Splatting and Neural Radiance Fields in Virtual Reality Fire Fighting
    Lian, Haojie
    Liu, Kangle
    Cao, Ruochen
    Fei, Ziheng
    Wen, Xin
    Chen, Leilei
    REMOTE SENSING, 2024, 16 (13)
  • [7] Interactive Video Manipulation Using Object Trajectories and Scene Backgrounds
    Shah, Rajvi
    Narayanan, P. J.
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 23 (09) : 1565 - 1576
  • [8] High-fidelity wheat plant reconstruction using 3D Gaussian splatting and neural radiance fields
    Stuart, Lewis A. G.
    Wells, Darren M.
    Atkinson, Jonathan A.
    Castle-Green, Simon
    Walker, Jack
    Pound, Michael P.
    GIGASCIENCE, 2025, 14
  • [9] The Potential of Neural Radiance Fields and 3D Gaussian Splatting for 3D Reconstruction from Aerial Imagery
    Haitz, Dennis
    Hermann, Max
    Roth, Aglaja Solana
    Weinmann, Michael
    Weinmann, Martin
    ISPRS ANNALS OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES: VOLUME X-2-2024, 2024, : 97 - 104
  • [10] HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video
    Liu, Jia-Wei
    Cao, Yan-Pei
    Yang, Tianyuan
    Xu, Zhongcong
    Keppo, Jussi
    Shan, Ying
    Qie, Xiaohu
    Shou, Mike Zheng
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 18437 - 18448