Report
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
| العنوان: | Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion |
|---|---|
| المؤلفون: | Liu, Fangfu, Wang, Hanyang, Yao, Shunyu, Zhang, Shengjun, Zhou, Jie, Duan, Yueqi |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Graphics |
| الوصف: | In recent years, there has been rapid development in 3D generation models, opening up new possibilities for applications such as simulating the dynamic movements of 3D objects and customizing their behaviors. However, current 3D generative models tend to focus only on surface features such as color and shape, neglecting the inherent physical properties that govern the behavior of objects in the real world. To accurately simulate physics-aligned dynamics, it is essential to predict the physical properties of materials and incorporate them into the behavior prediction process. Nonetheless, predicting the diverse materials of real-world objects is still challenging due to the complex nature of their physical attributes. In this paper, we propose \textbf{Physics3D}, a novel method for learning various physical properties of 3D objects through a video diffusion model. Our approach involves designing a highly generalizable physical simulation system based on a viscoelastic material model, which enables us to simulate a wide range of materials with high-fidelity capabilities. Moreover, we distill the physical priors from a video diffusion model that contains more understanding of realistic object materials. Extensive experiments demonstrate the effectiveness of our method with both elastic and plastic materials. Physics3D shows great potential for bridging the gap between the physical world and virtual neural space, providing a better integration and application of realistic physical principles in virtual environments. Project page: https://liuff19.github.io/Physics3D. Comment: Project page: https://liuff19.github.io/Physics3D |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.04338 |
| رقم الانضمام: | edsarx.2406.04338 |
| قاعدة البيانات: | arXiv |
| ResultId |
1 |
|---|---|
| Header |
edsarx arXiv edsarx.2406.04338 1112 3 Report report 1112.21606445313 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2406.04338&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => http://arxiv.org/abs/2406.04338 [Name] => EDS - Arxiv [Category] => fullText [Text] => View record in Arxiv [MouseOverText] => View record in Arxiv ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Liu%2C+Fangfu%22">Liu, Fangfu</searchLink><br /><searchLink fieldCode="AR" term="%22Wang%2C+Hanyang%22">Wang, Hanyang</searchLink><br /><searchLink fieldCode="AR" term="%22Yao%2C+Shunyu%22">Yao, Shunyu</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Shengjun%22">Zhang, Shengjun</searchLink><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Jie%22">Zhou, Jie</searchLink><br /><searchLink fieldCode="AR" term="%22Duan%2C+Yueqi%22">Duan, Yueqi</searchLink> ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2024 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => Computer Science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Graphics%22">Computer Science - Graphics</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => In recent years, there has been rapid development in 3D generation models, opening up new possibilities for applications such as simulating the dynamic movements of 3D objects and customizing their behaviors. However, current 3D generative models tend to focus only on surface features such as color and shape, neglecting the inherent physical properties that govern the behavior of objects in the real world. To accurately simulate physics-aligned dynamics, it is essential to predict the physical properties of materials and incorporate them into the behavior prediction process. Nonetheless, predicting the diverse materials of real-world objects is still challenging due to the complex nature of their physical attributes. In this paper, we propose \textbf{Physics3D}, a novel method for learning various physical properties of 3D objects through a video diffusion model. Our approach involves designing a highly generalizable physical simulation system based on a viscoelastic material model, which enables us to simulate a wide range of materials with high-fidelity capabilities. Moreover, we distill the physical priors from a video diffusion model that contains more understanding of realistic object materials. Extensive experiments demonstrate the effectiveness of our method with both elastic and plastic materials. Physics3D shows great potential for bridging the gap between the physical world and virtual neural space, providing a better integration and application of realistic physical principles in virtual environments. Project page: https://liuff19.github.io/Physics3D.<br />Comment: Project page: https://liuff19.github.io/Physics3D ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => Working Paper ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2406.04338" linkWindow="_blank">http://arxiv.org/abs/2406.04338</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsarx.2406.04338 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Computer Science - Computer Vision and Pattern Recognition
[Type] => general
)
[1] => Array
(
[SubjectFull] => Computer Science - Artificial Intelligence
[Type] => general
)
[2] => Array
(
[SubjectFull] => Computer Science - Graphics
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Liu, Fangfu
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Wang, Hanyang
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Yao, Shunyu
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Zhang, Shengjun
)
)
)
[4] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Zhou, Jie
)
)
)
[5] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Duan, Yueqi
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 06
[M] => 06
[Type] => published
[Y] => 2024
)
)
)
)
)
)
)
|
| IllustrationInfo |