Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.23589 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917046010249216 |
|---|---|
| author | Liang, Erich Bhattacharjee, Roma Dey, Sreemanti Moschopoulos, Rafael Wang, Caitlin Liao, Michel Tan, Grace Wang, Andrew Kayan, Karhan Alexandropoulos, Stamatis Deng, Jia |
| author_facet | Liang, Erich Bhattacharjee, Roma Dey, Sreemanti Moschopoulos, Rafael Wang, Caitlin Liao, Michel Tan, Grace Wang, Andrew Kayan, Karhan Alexandropoulos, Stamatis Deng, Jia |
| contents | Accurately tracking camera intrinsics is crucial for achieving 3D understanding from 2D video. However, most 3D algorithms assume that camera intrinsics stay constant throughout a video, which is often not true for many real-world in-the-wild videos. A major obstacle in this field is a lack of dynamic camera intrinsics benchmarks--existing benchmarks typically offer limited diversity in scene content and intrinsics variation, and none provide per-frame intrinsic changes for consecutive video frames. In this paper, we present Intrinsics in Flux (InFlux), a real-world benchmark that provides per-frame ground truth intrinsics annotations for videos with dynamic intrinsics. Compared to prior benchmarks, InFlux captures a wider range of intrinsic variations and scene diversity, featuring 143K+ annotated frames from 386 high-resolution indoor and outdoor videos with dynamic camera intrinsics. To ensure accurate per-frame intrinsics, we build a comprehensive lookup table of calibration experiments and extend the Kalibr toolbox to improve its accuracy and robustness. Using our benchmark, we evaluate existing baseline methods for predicting camera intrinsics and find that most struggle to achieve accurate predictions on videos with dynamic intrinsics. For the dataset, code, videos, and submission, please visit https://influx.cs.princeton.edu/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23589 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras Liang, Erich Bhattacharjee, Roma Dey, Sreemanti Moschopoulos, Rafael Wang, Caitlin Liao, Michel Tan, Grace Wang, Andrew Kayan, Karhan Alexandropoulos, Stamatis Deng, Jia Computer Vision and Pattern Recognition Accurately tracking camera intrinsics is crucial for achieving 3D understanding from 2D video. However, most 3D algorithms assume that camera intrinsics stay constant throughout a video, which is often not true for many real-world in-the-wild videos. A major obstacle in this field is a lack of dynamic camera intrinsics benchmarks--existing benchmarks typically offer limited diversity in scene content and intrinsics variation, and none provide per-frame intrinsic changes for consecutive video frames. In this paper, we present Intrinsics in Flux (InFlux), a real-world benchmark that provides per-frame ground truth intrinsics annotations for videos with dynamic intrinsics. Compared to prior benchmarks, InFlux captures a wider range of intrinsic variations and scene diversity, featuring 143K+ annotated frames from 386 high-resolution indoor and outdoor videos with dynamic camera intrinsics. To ensure accurate per-frame intrinsics, we build a comprehensive lookup table of calibration experiments and extend the Kalibr toolbox to improve its accuracy and robustness. Using our benchmark, we evaluate existing baseline methods for predicting camera intrinsics and find that most struggle to achieve accurate predictions on videos with dynamic intrinsics. For the dataset, code, videos, and submission, please visit https://influx.cs.princeton.edu/. |
| title | InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.23589 |