EUVIMEDEUVIMED entdecken
Crossref

Reconstructing 4D Spatial Intelligence: A Survey

Yukang Cao, Jiahao Lu, Zhisheng Huang, Zhuowen Shen, Chengfeng Zhao, Fangzhou Hong, Zhaoxi Chen, Xin Li, Wenping Wang, Yuan Liu, Ziwei Liu

International Journal of Computer Vision · 2026-11 · 134 (11)

DOI: 10.1007/s11263-026-03072-y ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 28.10.2026. Verfasst von Yukang Cao und 10 weiteren Autor:innen. Die Arbeit nennt 466 Literaturangaben. Gefördert von: Ministry of Education - Singapore.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range from entertainment domains like movies, where the focus is often on reconstructing fundamental visual elements, to embodied AI, which emphasizes interaction modeling and physical realism. Fueled by rapid advances in 3D representations and deep learning architectures, the field has evolved quickly, outpacing the scope of previous surveys. Additionally, existing surveys rarely offer a comprehensive analysis of the hierarchical structure of 4D scene reconstruction. To address this gap, we present a new perspective that organizes existing methods into five progressive levels of 4D spatial intelligence: (1) Level 1—reconstruction of low-level 3D cues (e.g., depth, pose, and point maps); (2) Level 2—reconstruction of 3D scene components (e.g., objects, humans, structures); (3) Level 3—reconstruction of 4D dynamic scenes; (4) Level 4—modeling of interactions among scene components; and (5) Level 5 – physically grounded 4D reconstruction. We conclude the survey by discussing the key challenges at each level and highlighting promising directions for advancing toward even richer levels of 4D spatial intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/yukangcao/Awesome-4D-Spatial-Intelligence.

Förderung

  • Ministry of Education - Singapore

Zitieren

APA

Cao, Y., Lu, J., Huang, Z., Shen, Z., Zhao, C., Hong, F., Chen, Z., Li, X., Wang, W., Liu, Y., & Liu, Z. (2026). Reconstructing 4D Spatial Intelligence: A Survey. International Journal of Computer Vision, 134(11). https://doi.org/10.1007/s11263-026-03072-y

Vancouver

Cao Y, Lu J, Huang Z, Shen Z, Zhao C, Hong F, et al. Reconstructing 4D Spatial Intelligence: A Survey. International Journal of Computer Vision. 2026;134(11). doi:10.1007/s11263-026-03072-y

BibTeX
@article{Cao2026,
  author = {Cao, Yukang and Lu, Jiahao and Huang, Zhisheng and Shen, Zhuowen and Zhao, Chengfeng and Hong, Fangzhou and Chen, Zhaoxi and Li, Xin and Wang, Wenping and Liu, Yuan and Liu, Ziwei},
  title = {Reconstructing 4D Spatial Intelligence: A Survey},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {11},
  doi = {10.1007/s11263-026-03072-y}
}
Kostenlos starten →