Jrender: An efficient differentiable rendering library based on Jittor
Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable render...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Hanggao Xin [verfasserIn] Chenzhong Xiang [verfasserIn] Wenyang Zhou [verfasserIn] Dun Liang [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
In: Graphical Models ; 130(2023), Seite 101202- volume:130 ; year:2023 ; pages:101202- |
|---|
| Links: |
|---|
| DOI / URN: |
10.1016/j.gmod.2023.101202 |
|---|
| Katalog-ID: |
DOAJ100171591 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ100171591 | ||
| 003 | DE-627 | ||
| 005 | 20240414070545.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240414s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.gmod.2023.101202 |2 doi | |
| 035 | |a (DE-627)DOAJ100171591 | ||
| 035 | |a (DE-599)DOAJ94725191eb9145098c68e3c228c90250 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 050 | 0 | |a T1-995 | |
| 100 | 0 | |a Hanggao Xin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Jrender: An efficient differentiable rendering library based on Jittor |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. | ||
| 650 | 4 | |a Differentiable rendering | |
| 650 | 4 | |a Real-time rendering | |
| 650 | 4 | |a Deep learning | |
| 653 | 0 | |a Science | |
| 653 | 0 | |a Q | |
| 653 | 0 | |a Technology (General) | |
| 700 | 0 | |a Chenzhong Xiang |e verfasserin |4 aut | |
| 700 | 0 | |a Wenyang Zhou |e verfasserin |4 aut | |
| 700 | 0 | |a Dun Liang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t Graphical Models |g 130(2023), Seite 101202- |
| 773 | 1 | 8 | |g volume:130 |g year:2023 |g pages:101202- |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.gmod.2023.101202 |z kostenfrei |
| 856 | 4 | 0 | |u https://doaj.org/article/94725191eb9145098c68e3c228c90250 |z kostenfrei |
| 856 | 4 | 0 | |u http://www.sciencedirect.com/science/article/pii/S1524070323000322 |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/1524-0703 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 951 | |a AR | ||
| 952 | |d 130 |j 2023 |h 101202- | ||
| author_variant |
h x hx c x cx w z wz d l dl |
|---|---|
| matchkey_str |
hanggaoxinchenzhongxiangwenyangzhoudunli:2023----:rneaefcetifrnibeedrnlb |
| hierarchy_sort_str |
2023 |
| callnumber-subject-code |
T |
| publishDate |
2023 |
| allfields |
10.1016/j.gmod.2023.101202 doi (DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 DE-627 ger DE-627 rakwb eng T1-995 Hanggao Xin verfasserin aut Jrender: An efficient differentiable rendering library based on Jittor 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) Chenzhong Xiang verfasserin aut Wenyang Zhou verfasserin aut Dun Liang verfasserin aut In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- https://doi.org/10.1016/j.gmod.2023.101202 kostenfrei https://doaj.org/article/94725191eb9145098c68e3c228c90250 kostenfrei http://www.sciencedirect.com/science/article/pii/S1524070323000322 kostenfrei https://doaj.org/toc/1524-0703 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 130 2023 101202- |
| spelling |
10.1016/j.gmod.2023.101202 doi (DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 DE-627 ger DE-627 rakwb eng T1-995 Hanggao Xin verfasserin aut Jrender: An efficient differentiable rendering library based on Jittor 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) Chenzhong Xiang verfasserin aut Wenyang Zhou verfasserin aut Dun Liang verfasserin aut In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- https://doi.org/10.1016/j.gmod.2023.101202 kostenfrei https://doaj.org/article/94725191eb9145098c68e3c228c90250 kostenfrei http://www.sciencedirect.com/science/article/pii/S1524070323000322 kostenfrei https://doaj.org/toc/1524-0703 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 130 2023 101202- |
| allfields_unstemmed |
10.1016/j.gmod.2023.101202 doi (DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 DE-627 ger DE-627 rakwb eng T1-995 Hanggao Xin verfasserin aut Jrender: An efficient differentiable rendering library based on Jittor 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) Chenzhong Xiang verfasserin aut Wenyang Zhou verfasserin aut Dun Liang verfasserin aut In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- https://doi.org/10.1016/j.gmod.2023.101202 kostenfrei https://doaj.org/article/94725191eb9145098c68e3c228c90250 kostenfrei http://www.sciencedirect.com/science/article/pii/S1524070323000322 kostenfrei https://doaj.org/toc/1524-0703 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 130 2023 101202- |
| allfieldsGer |
10.1016/j.gmod.2023.101202 doi (DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 DE-627 ger DE-627 rakwb eng T1-995 Hanggao Xin verfasserin aut Jrender: An efficient differentiable rendering library based on Jittor 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) Chenzhong Xiang verfasserin aut Wenyang Zhou verfasserin aut Dun Liang verfasserin aut In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- https://doi.org/10.1016/j.gmod.2023.101202 kostenfrei https://doaj.org/article/94725191eb9145098c68e3c228c90250 kostenfrei http://www.sciencedirect.com/science/article/pii/S1524070323000322 kostenfrei https://doaj.org/toc/1524-0703 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 130 2023 101202- |
| allfieldsSound |
10.1016/j.gmod.2023.101202 doi (DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 DE-627 ger DE-627 rakwb eng T1-995 Hanggao Xin verfasserin aut Jrender: An efficient differentiable rendering library based on Jittor 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) Chenzhong Xiang verfasserin aut Wenyang Zhou verfasserin aut Dun Liang verfasserin aut In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- https://doi.org/10.1016/j.gmod.2023.101202 kostenfrei https://doaj.org/article/94725191eb9145098c68e3c228c90250 kostenfrei http://www.sciencedirect.com/science/article/pii/S1524070323000322 kostenfrei https://doaj.org/toc/1524-0703 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 130 2023 101202- |
| language |
English |
| source |
In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- |
| sourceStr |
In Graphical Models 130(2023), Seite 101202- volume:130 year:2023 pages:101202- |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Differentiable rendering Real-time rendering Deep learning Science Q Technology (General) |
| isfreeaccess_bool |
true |
| container_title |
Graphical Models |
| authorswithroles_txt_mv |
Hanggao Xin @@aut@@ Chenzhong Xiang @@aut@@ Wenyang Zhou @@aut@@ Dun Liang @@aut@@ |
| publishDateDaySort_date |
2023-01-01T00:00:00Z |
| id |
DOAJ100171591 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ100171591</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414070545.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240414s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.gmod.2023.101202</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ100171591</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ94725191eb9145098c68e3c228c90250</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">T1-995</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Hanggao Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Jrender: An efficient differentiable rendering library based on Jittor</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Differentiable rendering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Real-time rendering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Science</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Q</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Technology (General)</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chenzhong Xiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wenyang Zhou</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dun Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Graphical Models</subfield><subfield code="g">130(2023), Seite 101202-</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:130</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:101202-</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.gmod.2023.101202</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/94725191eb9145098c68e3c228c90250</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://www.sciencedirect.com/science/article/pii/S1524070323000322</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1524-0703</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">130</subfield><subfield code="j">2023</subfield><subfield code="h">101202-</subfield></datafield></record></collection>
|
| callnumber-first |
T - Technology |
| author |
Hanggao Xin |
| spellingShingle |
Hanggao Xin misc T1-995 misc Differentiable rendering misc Real-time rendering misc Deep learning misc Science misc Q misc Technology (General) Jrender: An efficient differentiable rendering library based on Jittor |
| authorStr |
Hanggao Xin |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut |
| collection |
DOAJ |
| remote_str |
true |
| callnumber-label |
T1-995 |
| illustrated |
Not Illustrated |
| topic_title |
T1-995 Jrender: An efficient differentiable rendering library based on Jittor Differentiable rendering Real-time rendering Deep learning |
| topic |
misc T1-995 misc Differentiable rendering misc Real-time rendering misc Deep learning misc Science misc Q misc Technology (General) |
| topic_unstemmed |
misc T1-995 misc Differentiable rendering misc Real-time rendering misc Deep learning misc Science misc Q misc Technology (General) |
| topic_browse |
misc T1-995 misc Differentiable rendering misc Real-time rendering misc Deep learning misc Science misc Q misc Technology (General) |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Graphical Models |
| hierarchy_top_title |
Graphical Models |
| isfreeaccess_txt |
true |
| title |
Jrender: An efficient differentiable rendering library based on Jittor |
| ctrlnum |
(DE-627)DOAJ100171591 (DE-599)DOAJ94725191eb9145098c68e3c228c90250 |
| title_full |
Jrender: An efficient differentiable rendering library based on Jittor |
| author_sort |
Hanggao Xin |
| journal |
Graphical Models |
| journalStr |
Graphical Models |
| callnumber-first-code |
T |
| lang_code |
eng |
| isOA_bool |
true |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
txt |
| container_start_page |
101202 |
| author_browse |
Hanggao Xin Chenzhong Xiang Wenyang Zhou Dun Liang |
| container_volume |
130 |
| class |
T1-995 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Hanggao Xin |
| doi_str_mv |
10.1016/j.gmod.2023.101202 |
| author2-role |
verfasserin |
| title_sort |
jrender: an efficient differentiable rendering library based on jittor |
| callnumber |
T1-995 |
| title_auth |
Jrender: An efficient differentiable rendering library based on Jittor |
| abstract |
Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. |
| abstractGer |
Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. |
| abstract_unstemmed |
Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ |
| title_short |
Jrender: An efficient differentiable rendering library based on Jittor |
| url |
https://doi.org/10.1016/j.gmod.2023.101202 https://doaj.org/article/94725191eb9145098c68e3c228c90250 http://www.sciencedirect.com/science/article/pii/S1524070323000322 https://doaj.org/toc/1524-0703 |
| remote_bool |
true |
| author2 |
Chenzhong Xiang Wenyang Zhou Dun Liang |
| author2Str |
Chenzhong Xiang Wenyang Zhou Dun Liang |
| callnumber-subject |
T - General Technology |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| doi_str |
10.1016/j.gmod.2023.101202 |
| callnumber-a |
T1-995 |
| up_date |
2024-07-04T01:49:53.650Z |
| _version_ |
1803611321036439552 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ100171591</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414070545.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240414s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.gmod.2023.101202</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ100171591</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ94725191eb9145098c68e3c228c90250</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">T1-995</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Hanggao Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Jrender: An efficient differentiable rendering library based on Jittor</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Differentiable rendering has been proven as a powerful tool to bridge 2D images and 3D models. With the aid of differentiable rendering, tasks in computer vision and computer graphics could be solved more elegantly and accurately. To address challenges in the implementations of differentiable rendering methods, we present an efficient and modular differentiable rendering library named Jrender based on Jittor. Jrender supports surface rendering for 3D meshes and volume rendering for 3D volumes. Compared with previous differentiable renderers, Jrender exhibits a significant improvement in both performance and rendering quality. Due to the modular design, various rendering effects such as PBR materials shading, ambient occlusions, soft shadows, global illumination, and subsurface scattering could be easily supported in Jrender, which are not available in other differentiable rendering libraries. To validate our library, we integrate Jrender into applications such as 3D object reconstruction and NeRF, which show that our implementations could achieve the same quality with higher performance.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Differentiable rendering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Real-time rendering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Science</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Q</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Technology (General)</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chenzhong Xiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wenyang Zhou</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dun Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Graphical Models</subfield><subfield code="g">130(2023), Seite 101202-</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:130</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:101202-</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.gmod.2023.101202</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/94725191eb9145098c68e3c228c90250</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://www.sciencedirect.com/science/article/pii/S1524070323000322</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1524-0703</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">130</subfield><subfield code="j">2023</subfield><subfield code="h">101202-</subfield></datafield></record></collection>
|
| score |
7.4004383 |