IM360: Large-scale Indoor Mapping with 360 Cameras
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914059746541568 |
|---|---|
| author | Jung, Dongki Choi, Jaehoon Lee, Yonghan Manocha, Dinesh |
| author_facet | Jung, Dongki Choi, Jaehoon Lee, Yonghan Manocha, Dinesh |
| contents | We present a novel 3D mapping pipeline for large-scale indoor environments. To address the significant challenges in large-scale indoor scenes, such as prevalent occlusions and textureless regions, we propose IM360, a novel approach that leverages the wide field of view of omnidirectional images and integrates the spherical camera model into the Structure-from-Motion (SfM) pipeline. Our SfM utilizes dense matching features specifically designed for 360 images, demonstrating superior capability in image registration. Furthermore, with the aid of mesh-based neural rendering techniques, we introduce a texture optimization method that refines texture maps and accurately captures view-dependent properties by combining diffuse and specular components. We evaluate our pipeline on large-scale indoor scenes, demonstrating its effectiveness in real-world scenarios. In practice, IM360 demonstrates superior performance, achieving a 3.5 PSNR increase in textured mesh reconstruction. We attain state-of-the-art performance in terms of camera localization and registration on Matterport3D and Stanford2D3D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IM360: Large-scale Indoor Mapping with 360 Cameras Jung, Dongki Choi, Jaehoon Lee, Yonghan Manocha, Dinesh Computer Vision and Pattern Recognition We present a novel 3D mapping pipeline for large-scale indoor environments. To address the significant challenges in large-scale indoor scenes, such as prevalent occlusions and textureless regions, we propose IM360, a novel approach that leverages the wide field of view of omnidirectional images and integrates the spherical camera model into the Structure-from-Motion (SfM) pipeline. Our SfM utilizes dense matching features specifically designed for 360 images, demonstrating superior capability in image registration. Furthermore, with the aid of mesh-based neural rendering techniques, we introduce a texture optimization method that refines texture maps and accurately captures view-dependent properties by combining diffuse and specular components. We evaluate our pipeline on large-scale indoor scenes, demonstrating its effectiveness in real-world scenarios. In practice, IM360 demonstrates superior performance, achieving a 3.5 PSNR increase in textured mesh reconstruction. We attain state-of-the-art performance in terms of camera localization and registration on Matterport3D and Stanford2D3D. |
| title | IM360: Large-scale Indoor Mapping with 360 Cameras |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12545 |