Daniil Sinitsyn — accepted AI-conference papers

2025

PRaDA: Projective Radial Distortion Averaging

Daniil Sinitsyn, Linus Härenstam-Nielsen, Daniel Cremers

CVPR 2025poster

We tackle the problem of automatic calibration of radially distorted cameras in challenging conditions. Accurately determining distortion parameters typically requires either 1) solving the full Structure from Motion (SfM) problem involving camera poses, 3D points, and the distortion parameters, whi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment

Sergei Solonets, Daniil Sinitsyn, Lukas Von Stumberg, Nikita Araslanov, Daniel Cremers

ICLR 2024oral

Direct image alignment is a widely used technique for relative 6DoF pose estimation between two images, but its accuracy strongly depends on pose initialization. Therefore, recent end-to-end frameworks increase the convergence basin of the learned feature descriptors with special training objectives…

Cited by 0 Source ↗PDF ↗Scholar ↗