On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
Andreas Meuleman, Ishaan Shah, Alexandre Lanvin, Bernhard Kerbl, George Drettakis

TL;DR
This paper introduces a fast, on-the-fly method for reconstructing large-scale scenes and estimating camera poses from unposed images, enabling immediate free-viewpoint navigation after capture.
Contribution
It presents a novel, scalable approach combining rapid pose estimation and Gaussian primitive sampling for real-time large-scale scene reconstruction.
Findings
Achieves real-time processing of diverse capture scenarios
Maintains high image quality comparable to slower methods
Handles wide-baseline and dense captures efficiently
Abstract
Radiance field methods such as 3D Gaussian Splatting (3DGS) allow easy reconstruction from photos, enabling free-viewpoint navigation. Nonetheless, pose estimation using Structure from Motion and 3DGS optimization can still each take between minutes and hours of computation after capture is complete. SLAM methods combined with 3DGS are fast but struggle with wide camera baselines and large scenes. We present an on-the-fly method to produce camera poses and a trained 3DGS immediately after capture. Our method can handle dense and wide-baseline captures of ordered photo sequences and large-scale scenes. To do this, we first introduce fast initial pose estimation, exploiting learned features and a GPU-friendly mini bundle adjustment. We then introduce direct sampling of Gaussian primitive positions and shapes, incrementally spawning primitives where required, significantly accelerating…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
