InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos. Consequently, estimating per-frame intrinsics from RGB images is critical for making 3D methods robust to videos with dynamic intrinsics. InFlux previously advanced this research direction by establishing the first real-world benchmark with per-frame ground truth intrinsics for dynamic intrinsics videos. Nevertheless, existing methods remain inaccurate due to two obstacles: (i) training data is scarce and lacks intrinsics diversity; and (ii) benchmarks, including InFlux, have limited...
| Authors | Erich Liang, Caleb Kha-Uong, Chinmaya Saran et al. |
|---|---|
| Primary category | cs.CV |
| Published | 6 July 2026 |
| Last updated at source | 5 September 2026 |
Connected in the knowledge graph
- princeton-vl/InFlux-RealDataset · cited by
- princeton-vl/InFlux-SynthDataset · cited by
Models and datasets referencing this paper
- princeton-vl/InFlux-SynthDataset
- princeton-vl/InFlux-RealDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.