“Projecting Radiance Fields to Mesh Surfaces with Local Space Texture Mapping” by Wei Lim, Xian Ng, Kyger, Michigami and Baghernezhad
Conference:
Type(s):
Title:
- Projecting Radiance Fields to Mesh Surfaces with Local Space Texture Mapping
Session/Category Title: Rendering & Displays
Presenter(s)/Author(s):
Abstract:
Radiance fields produce high fidelity images with high rendering speed, but are difficult to manipulate. We perform avatar texture transfer by combining benefits from radiance fields and mesh surfaces. The source is represented using 3D Gaussian Splatter, then Gaussians projected onto target mesh. The projection completes in 1.12s in CPU.
References:
[1]
Bernhard Kerbl, Georgios Kopanas, Thomas Leimk?hler, and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. arxiv:2308.04079 [cs.GR]
[2]
Adrian Xuan Wei Lim, Lynnette Hui Xian Ng, Conor Griffin, Nicholas Kryer, and Faraz Baghernezhad. 2023. Reverse Projection: Real-Time Local Space Texture Mapping. In ACM SIGGRAPH 2023 Posters (Los Angeles, CA, USA) (SIGGRAPH ?23). Association for Computing Machinery, New York, NY, USA, Article 48, 2 pages. https://doi.org/10.1145/3588028.3603653
[3]
Aymen Mir, Thiemo Alldieck, and Gerard Pons-Moll. 2020. Learning to transfer texture from clothing images to 3d humans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7023?7034.
[4]
Patrick Schmidt, D?rte Pieper, and Leif Kobbelt. 2023. Surface Maps via Adaptive Triangulations. Computer Graphics Forum 42, 2 (2023).
[5]
Aliaksandra Shysheya, Egor Zakharov, Kara-Ali Aliev, Renat Bashirov, Egor Burkov, Karim Iskakov, Aleksei Ivakhnenko, Yury Malkov, Igor Pasechnik, Dmitry Ulyanov, 2019. Textured neural avatars. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2387?2397.
[6]
Xiangzhi Eric Wang and Zackary P. T. Sin. 2024. 3D Gaussian Model for Animation and Texturing. arxiv:2402.19441 [cs.GR]
