No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914355828752384 |
|---|---|
| author | Wu, Cho-Ying Huang, Zixun Huang, Xinyu Ren, Liu |
| author_facet | Wu, Cho-Ying Huang, Zixun Huang, Xinyu Ren, Liu |
| contents | We present the first study of cross-sensor view synthesis across different modalities. We examine a practical, fundamental, yet widely overlooked problem: getting aligned RGB-X data, where most RGB-X prior work assumes such pairs exist and focuses on modality fusion, but it empirically requires huge engineering effort in calibration. We propose a match-densify-consolidate method. First, we perform RGB-X image matching followed by guided point densification. Using the proposed confidence-aware densification and self-matching filtering, we attain better view synthesis and later consolidate them in 3D Gaussian Splatting (3DGS). Our method uses no 3D priors for X-sensor and only assumes nearly no-cost COLMAP for RGB. We aim to remove the cumbersome calibration for various RGB-X sensors and advance the popularity of cross-sensor learning by a scalable solution that breaks through the bottleneck in large-scale real-world RGB-X data collection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23559 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency Wu, Cho-Ying Huang, Zixun Huang, Xinyu Ren, Liu Computer Vision and Pattern Recognition We present the first study of cross-sensor view synthesis across different modalities. We examine a practical, fundamental, yet widely overlooked problem: getting aligned RGB-X data, where most RGB-X prior work assumes such pairs exist and focuses on modality fusion, but it empirically requires huge engineering effort in calibration. We propose a match-densify-consolidate method. First, we perform RGB-X image matching followed by guided point densification. Using the proposed confidence-aware densification and self-matching filtering, we attain better view synthesis and later consolidate them in 3D Gaussian Splatting (3DGS). Our method uses no 3D priors for X-sensor and only assumes nearly no-cost COLMAP for RGB. We aim to remove the cumbersome calibration for various RGB-X sensors and advance the popularity of cross-sensor learning by a scalable solution that breaks through the bottleneck in large-scale real-world RGB-X data collection. |
| title | No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23559 |