InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908075985731584 |
|---|---|
| author | Lee, Seunghwan Park, Gwanmo Son, Hyewon Ryu, Jiwon Chae, Han Joo |
| author_facet | Lee, Seunghwan Park, Gwanmo Son, Hyewon Ryu, Jiwon Chae, Han Joo |
| contents | We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous methods that have employed feature encoding to improve optimization speed, we further improve the reconstruction quality with minimal impact on optimization time by refining depth information. InFusionSurf addresses camera motion-induced blurs in each depth frame through a per-frame intrinsic refinement scheme. It incorporates the truncated signed distance field (TSDF) Fusion, a classical real-time 3D surface reconstruction method, as a pretraining tool for the feature grid, enhancing reconstruction details and training speed. Comparative quantitative and qualitative analyses show that InFusionSurf reconstructs scenes with high accuracy while maintaining optimization efficiency. The effectiveness of our intrinsic refinement and TSDF Fusion-based pretraining is further validated through an ablation study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_04508 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning Lee, Seunghwan Park, Gwanmo Son, Hyewon Ryu, Jiwon Chae, Han Joo Computer Vision and Pattern Recognition We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous methods that have employed feature encoding to improve optimization speed, we further improve the reconstruction quality with minimal impact on optimization time by refining depth information. InFusionSurf addresses camera motion-induced blurs in each depth frame through a per-frame intrinsic refinement scheme. It incorporates the truncated signed distance field (TSDF) Fusion, a classical real-time 3D surface reconstruction method, as a pretraining tool for the feature grid, enhancing reconstruction details and training speed. Comparative quantitative and qualitative analyses show that InFusionSurf reconstructs scenes with high accuracy while maintaining optimization efficiency. The effectiveness of our intrinsic refinement and TSDF Fusion-based pretraining is further validated through an ablation study. |
| title | InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.04508 |