D-TensoRF : tensorial radiance fields for dynamic scenes움직임이 있는 장면을 모델링하기 위한 텐서 라디언스 필드 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 264
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorKim, Daeyoung-
dc.contributor.advisor김대영-
dc.contributor.authorJang, Hankyu-
dc.date.accessioned2023-06-26T19:31:16Z-
dc.date.available2023-06-26T19:31:16Z-
dc.date.issued2023-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032982&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/309501-
dc.description학위논문(석사) - 한국과학기술원 : 전산학부, 2023.2,[v, 31 p. :]-
dc.description.abstractNeural radiance field (NeRF) attracts attention as a promising approach to reconstructing the 3D scene. As NeRF emerges, subsequent studies have been conducted to model dynamic scenes, which include motions or topological changes. However, most of them use an additional deformation network, slowing down the training and rendering speed. Tensorial radiance field (TensoRF) recently shows its potential for fast, high-quality reconstruction of static scenes with compact model size. In this paper, we present D-TensoRF, a tensorial radiance field for dynamic scenes, enabling novel view synthesis at a specific time. We consider the radiance field of a dynamic scene as a 5D tensor. The 5D tensor represents a 4D grid in which each axis corresponds to X, Y, Z, and time and has 1D multi-channel features per element. Similar to TensoRF, we decompose the grid either into rank-one vector components (CP decomposition) or low-rank matrix components (newly proposed MM decomposition). We also use smoothing regularization to reflect the relationship between features at different times (temporal dependency). We conduct extensive evaluations to analyze our models. We show that D-TensoRF with CP decomposition and MM decomposition both have short training times and significantly low memory footprints with quantitatively and qualitatively competitive rendering results in comparison to the state-of-the-art methods in 3D dynamic scene modeling.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectNeural radiance field▼aDynamic scene modeling▼aTensor decomposition-
dc.subject뉴럴 라이언스 필드▼a동적 장면 모델링▼a텐서 분해-
dc.titleD-TensoRF-
dc.title.alternative움직임이 있는 장면을 모델링하기 위한 텐서 라디언스 필드 연구-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전산학부,-
dc.contributor.alternativeauthor장한규-
dc.title.subtitletensorial radiance fields for dynamic scenes-
Appears in Collection
CS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0