Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2306.09322 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912888886657024 |
|---|---|
| author | Zhu, Shizhan Saito, Shunsuke Bozic, Aljaz Aliaga, Carlos Darrell, Trevor Lassner, Christoph |
| author_facet | Zhu, Shizhan Saito, Shunsuke Bozic, Aljaz Aliaga, Carlos Darrell, Trevor Lassner, Christoph |
| contents | Image-based lighting (IBL) is a widely used technique that renders objects using a high dynamic range image or environment map. However, aggregating the irradiance at the object's surface is computationally expensive, in particular for non-opaque, translucent materials that require volumetric rendering techniques. In this paper we present a fast neural 3D reconstruction and relighting model that extends volumetric implicit models such as neural radiance fields to be relightable using IBL. It is general enough to handle materials that exhibit complex light transport effects, such as translucency and glossy reflections from detailed surface geometry, producing realistic and compelling results. Rendering can be within a second at 800$\times$800 resolution (0.72s on an NVIDIA 3090 GPU and 0.30s on an A100 GPU) without engineering optimization. Our code and dataset are available at https://zhusz.github.io/TRHM-Webpage/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_09322 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fast Image-based Neural Relighting with Translucency-Reflection Modeling Zhu, Shizhan Saito, Shunsuke Bozic, Aljaz Aliaga, Carlos Darrell, Trevor Lassner, Christoph Computer Vision and Pattern Recognition Image-based lighting (IBL) is a widely used technique that renders objects using a high dynamic range image or environment map. However, aggregating the irradiance at the object's surface is computationally expensive, in particular for non-opaque, translucent materials that require volumetric rendering techniques. In this paper we present a fast neural 3D reconstruction and relighting model that extends volumetric implicit models such as neural radiance fields to be relightable using IBL. It is general enough to handle materials that exhibit complex light transport effects, such as translucency and glossy reflections from detailed surface geometry, producing realistic and compelling results. Rendering can be within a second at 800$\times$800 resolution (0.72s on an NVIDIA 3090 GPU and 0.30s on an A100 GPU) without engineering optimization. Our code and dataset are available at https://zhusz.github.io/TRHM-Webpage/. |
| title | Fast Image-based Neural Relighting with Translucency-Reflection Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.09322 |