東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Challenges in 3D Machine Learning: D...

Uy, Mikaela Angelina,

FindBook

Google Book

Amazon

博客來

Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness // Mikaela Angelina Uy.
作者:	Uy, Mikaela Angelina,
面頁冊數:	1 electronic resource (144 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: A.
Contained By:	Dissertations Abstracts International86-05A.
標題:	Ambiguity. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31652055
ISBN:	9798346390992

Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness /
Uy, Mikaela Angelina,

Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness /Mikaela Angelina Uy. - 1 electronic resource (144 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: A.

3D content creation is an important and increasingly popular task for different applications such as graphic design, gaming and animation, virtual reality experiences, manufacturing, and robotics. This growing popularity creates a strong demand for tools that facilitate the creation and synthesis of new 3D content. Traditionally, designers would need to manually design and create each new model, which is a difficult and labor intensive task, requiring expert knowledge of 3D modeling or computer-aided design (CAD) tools. With the advent of 3D machine learning, there is an opportunity to make the 3D creation process more accessible -- but there are challenges on the way. For example, difficulties arise when 3D data repositories of sufficient quality and size are not available, making approaches that require 3D supervision implausible. Another difficulty occurs when structure-aware, fine-grained control or further manipulation and editing is desired for the output, a task for which coarse homogeneous 3D representations are not ideal. In this dissertation, we address two important challenges in 3D machine learning, namely data scarcity and structure-awareness, thus taking promising steps towards automating more parts of the 3D content creation process.First, we introduce a novel approach for reconstructing a 3D scene when no 3D data is available for direct supervision at training time and instead only a sparse set of image captures are given. We show that by introducing some advances in neural rendering, we are able to coarsely reconstruct a 3D scene from only few 2D input views by modeling ambiguity-aware depth estimates. Moreover, we additionally introduce a new image formation model that allows better neural-rendering-based geometric reconstruction. Second, we address the challenge of creating 3D content that is structure-aware, allowing for the creation of 3D assets with a fine level of geometric detail as well as enabling further user manipulation and editing. Concretely, we propose an approach that leverages existing artist-generated databases (meshes) to create controllable deformations of existing 3D data by conditioning on target images or scans. We also study learning representations of shapes that are more structured, e.g., CAD models, and are directly editable, thus improving user control. Depending on the task, use-case and user preference, these techniques offer different advantages towards making 3D content creation more universally accessible.

English

ISBN: 9798346390992Subjects--Topical Terms:

659528
Ambiguity.

Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness /
LDR:03826nmm a22003853i 4500 001 2432608
005 20250731101855.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798346390992
035 $a (MiAaPQD)AAI31652055
035 $a (MiAaPQD)Stanfordpr895qw3725
035 $a AAI31652055
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Uy, Mikaela Angelina, $e author. $3 3821900
245 1 0 $a Challenges in 3D Machine Learning: Data Scarcity and Structure-Awareness / $c Mikaela Angelina Uy.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (144 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-05, Section: A.
500 $a Advisors: Guibas, Leonidas Committee members: Bohg, Jeannette; Wetzstein, Gordon; Bent, Stacey F.
502 $b Ph.D. $c Stanford University $d 2024.
520 $a 3D content creation is an important and increasingly popular task for different applications such as graphic design, gaming and animation, virtual reality experiences, manufacturing, and robotics. This growing popularity creates a strong demand for tools that facilitate the creation and synthesis of new 3D content. Traditionally, designers would need to manually design and create each new model, which is a difficult and labor intensive task, requiring expert knowledge of 3D modeling or computer-aided design (CAD) tools. With the advent of 3D machine learning, there is an opportunity to make the 3D creation process more accessible -- but there are challenges on the way. For example, difficulties arise when 3D data repositories of sufficient quality and size are not available, making approaches that require 3D supervision implausible. Another difficulty occurs when structure-aware, fine-grained control or further manipulation and editing is desired for the output, a task for which coarse homogeneous 3D representations are not ideal. In this dissertation, we address two important challenges in 3D machine learning, namely data scarcity and structure-awareness, thus taking promising steps towards automating more parts of the 3D content creation process.First, we introduce a novel approach for reconstructing a 3D scene when no 3D data is available for direct supervision at training time and instead only a sparse set of image captures are given. We show that by introducing some advances in neural rendering, we are able to coarsely reconstruct a 3D scene from only few 2D input views by modeling ambiguity-aware depth estimates. Moreover, we additionally introduce a new image formation model that allows better neural-rendering-based geometric reconstruction. Second, we address the challenge of creating 3D content that is structure-aware, allowing for the creation of 3D assets with a fine level of geometric detail as well as enabling further user manipulation and editing. Concretely, we propose an approach that leverages existing artist-generated databases (meshes) to create controllable deformations of existing 3D data by conditioning on target images or scans. We also study learning representations of shapes that are more structured, e.g., CAD models, and are directly editable, thus improving user control. Depending on the task, use-case and user preference, these techniques offer different advantages towards making 3D content creation more universally accessible.
546 $a English
590 $a School code: 0212
650 4 $a Ambiguity. $3 659528
650 4 $a Deformation. $2 lcstt $3 3267001
650 4 $a Deadlines. $3 3697467
650 4 $a Semantics. $3 520060
650 4 $a Logic. $3 529544
650 4 $a Engineering. $3 586835
690 $a 0800
690 $a 0395
690 $a 0537
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Guibas, Leonidas $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05A.
790 $a 0212
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31652055