Fast View Synthesis of Casual Videos with Soup-of-Planes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916329860104192 |
|---|---|
| author | Lee, Yao-Chih Zhang, Zhoutong Blackburn-Matzen, Kevin Niklaus, Simon Zhang, Jianming Huang, Jia-Bin Liu, Feng |
| author_facet | Lee, Yao-Chih Zhang, Zhoutong Blackburn-Matzen, Kevin Niklaus, Simon Zhang, Jianming Huang, Jia-Bin Liu, Feng |
| contents | Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02135 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fast View Synthesis of Casual Videos with Soup-of-Planes Lee, Yao-Chih Zhang, Zhoutong Blackburn-Matzen, Kevin Niklaus, Simon Zhang, Jianming Huang, Jia-Bin Liu, Feng Computer Vision and Pattern Recognition Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering. |
| title | Fast View Synthesis of Casual Videos with Soup-of-Planes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.02135 |