InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics

Summary

InFlux++ is a dataset and benchmark suite for estimating dynamic camera intrinsics from video. Camera intrinsics are critical for recovering 3D structure from 2D video, yet most 3D algorithms assume fixed intrinsics, an assumption often violated by real-world footage. InFlux++ consists of two components: InFlux++ Synth, a large-scale procedurally generated synthetic video dataset with over 441,000 annotated frames and 1,841 high-resolution videos providing accurate per-frame ground-truth intrinsics, and InFlux++ Real, an expanded real-world benchmark adding over 514,000 frames and 334 high-resolution videos. Experiments show that fine-tuning existing intrinsics-prediction methods on InFlux++ Synth improves focal-length estimation accuracy on both real-world benchmarks, demonstrating that synthetic supervision is a promising approach for RGB-based camera intrinsics prediction. The project website is https://influx.cs.princeton.edu/. Paper ID: arXiv:2607.05389.