EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Jingnan, Chen, Zhuo, Yan, Yichao, Pan, Bowen, Wang, Zhe, Lyu, Jiangjing, Yang, Xiaokang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913590560161792
author Gao, Jingnan
Chen, Zhuo
Yan, Yichao
Pan, Bowen
Wang, Zhe
Lyu, Jiangjing
Yang, Xiaokang
author_facet Gao, Jingnan
Chen, Zhuo
Yan, Yichao
Pan, Bowen
Wang, Zhe
Lyu, Jiangjing
Yang, Xiaokang
contents Reconstructing real-world 3D objects has numerous applications in computer vision, such as virtual reality, video games, and animations. Ideally, 3D reconstruction methods should generate high-fidelity results with 3D consistency in real-time. Traditional methods match pixels between images using photo-consistency constraints or learned features, while differentiable rendering methods like Neural Radiance Fields (NeRF) use differentiable volume rendering or surface-based representation to generate high-fidelity scenes. However, these methods require excessive runtime for rendering, making them impractical for daily applications. To address these challenges, we present $\textbf{EvaSurf}$, an $\textbf{E}$fficient $\textbf{V}$iew-$\textbf{A}$ware implicit textured $\textbf{Surf}$ace reconstruction method. In our method, we first employ an efficient surface-based model with a multi-view supervision module to ensure accurate mesh reconstruction. To enable high-fidelity rendering, we learn an implicit texture embedded with view-aware encoding to capture view-dependent information. Furthermore, with the explicit geometry and the implicit texture, we can employ a lightweight neural shader to reduce the expense of computation and further support real-time rendering on common mobile devices. Extensive experiments demonstrate that our method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets. Moreover, our method can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40 FPS (Frames Per Second), with a final package required for rendering taking up only 40-50 MB.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09806
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction
Gao, Jingnan
Chen, Zhuo
Yan, Yichao
Pan, Bowen
Wang, Zhe
Lyu, Jiangjing
Yang, Xiaokang
Computer Vision and Pattern Recognition
Reconstructing real-world 3D objects has numerous applications in computer vision, such as virtual reality, video games, and animations. Ideally, 3D reconstruction methods should generate high-fidelity results with 3D consistency in real-time. Traditional methods match pixels between images using photo-consistency constraints or learned features, while differentiable rendering methods like Neural Radiance Fields (NeRF) use differentiable volume rendering or surface-based representation to generate high-fidelity scenes. However, these methods require excessive runtime for rendering, making them impractical for daily applications. To address these challenges, we present $\textbf{EvaSurf}$, an $\textbf{E}$fficient $\textbf{V}$iew-$\textbf{A}$ware implicit textured $\textbf{Surf}$ace reconstruction method. In our method, we first employ an efficient surface-based model with a multi-view supervision module to ensure accurate mesh reconstruction. To enable high-fidelity rendering, we learn an implicit texture embedded with view-aware encoding to capture view-dependent information. Furthermore, with the explicit geometry and the implicit texture, we can employ a lightweight neural shader to reduce the expense of computation and further support real-time rendering on common mobile devices. Extensive experiments demonstrate that our method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets. Moreover, our method can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40 FPS (Frames Per Second), with a final package required for rendering taking up only 40-50 MB.
title EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.09806