國立虎尾科技大學 |

Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS).

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS)./
作者:	Kim, Nahyeon.
面頁冊數:	1 online resource (51 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798382903804

Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS).
Kim, Nahyeon.

Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS). - 1 online resource (51 pages)

Source: Masters Abstracts International, Volume: 85-12.

Thesis (M.S.)--University of California, Los Angeles, 2024.

Includes bibliographical references

Neural Radiance Fields (NeRF) have recently emerged as a promising research area due to their remarkable photorealistic rendering capabilities and diverse applications. By training NeRF network with various viewpoints and their corresponding images, we can generate new views of a scene. This approach, however, is highly dependent on the quality and composition of the training images. Effective learning in NeRF can be achieved by selecting images with high coverage rather than those having many overlaps. To date, there has been a lack of research focused on the selection of images for NeRF training. To address this gap, this paper proposes an innovative image selector designed to select optimal image viewpoints to enhance NeRF training. We created a custom dataset by creating a virtual environment in Unity, allowing for the flexible positioning of cameras to capture images. We introduce two methods to predict optimal image viewpoints: the first employs reinforcement learning, while the second utilizes a Self-supervised NeRF Image Selector (SNIS) based on a simplified deep neural network architecture. SNIS is trained using our novel pseudo-labels, which function analogously to the reward mechanism in reinforcement learning frameworks. Experimental results demonstrate that our selector significantly outperforms the random selection of images, providing more stable and superior performance in NeRF training.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382903804Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Computer visionIndex Terms--Genre/Form:

554714
Electronic books.

Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS).
LDR:02788ntm a22003857 4500 001 1150219
005 20241022111616.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382903804
035 $a (MiAaPQ)AAI31331709
035 $a AAI31331709
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kim, Nahyeon. $3 1476662
245 1 0 $a Advancing Neural Radiance Fields Through Self-Supervised NeRF Image Selector (SNIS).
264 0 $c 2024
300 $a 1 online resource (51 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: Masters Abstracts International, Volume: 85-12.
500 $a Advisor: Jawed, Mohammad Khalid.
502 $a Thesis (M.S.)--University of California, Los Angeles, 2024.
504 $a Includes bibliographical references
520 $a Neural Radiance Fields (NeRF) have recently emerged as a promising research area due to their remarkable photorealistic rendering capabilities and diverse applications. By training NeRF network with various viewpoints and their corresponding images, we can generate new views of a scene. This approach, however, is highly dependent on the quality and composition of the training images. Effective learning in NeRF can be achieved by selecting images with high coverage rather than those having many overlaps. To date, there has been a lack of research focused on the selection of images for NeRF training. To address this gap, this paper proposes an innovative image selector designed to select optimal image viewpoints to enhance NeRF training. We created a custom dataset by creating a virtual environment in Unity, allowing for the flexible positioning of cameras to capture images. We introduce two methods to predict optimal image viewpoints: the first employs reinforcement learning, while the second utilizes a Self-supervised NeRF Image Selector (SNIS) based on a simplified deep neural network architecture. SNIS is trained using our novel pseudo-labels, which function analogously to the reward mechanism in reinforcement learning frameworks. Experimental results demonstrate that our selector significantly outperforms the random selection of images, providing more stable and superior performance in NeRF training.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Information technology. $3 559429
653 $a Computer vision
653 $a Machine learning
653 $a Neural Radiance Fields
653 $a Reinforcement learning agent
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0489
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Los Angeles. $b Mechanical Engineering 0330. $3 1148505
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31331709 $z click for full text (PQDT)