Felix Wimbauer
@fwimbauer.bsky.social
ELLIS PhD Student in Computer Vision at TUM with Daniel Cremers and Christian Rupprecht (Oxford), fwmb.github.io, prev. Research Intern at Meta GenAI
While recent methods like Monst3r achieve impressive results, they require datasets with camera pose labels. Such datasets are hard to collect and not available for every domain. AnyCam can directly be trained on any video dataset.
More details: fwmb.github.io/anycam
More details: fwmb.github.io/anycam
May 13, 2025 at 8:11 AM
While recent methods like Monst3r achieve impressive results, they require datasets with camera pose labels. Such datasets are hard to collect and not available for every domain. AnyCam can directly be trained on any video dataset.
More details: fwmb.github.io/anycam
More details: fwmb.github.io/anycam
ArXiV: arxiv.org/abs/2503.23282
Code and models: github.com/Brummi/anycam
Project page: fwmb.github.io/anycam/
Code and models: github.com/Brummi/anycam
Project page: fwmb.github.io/anycam/
AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
Estimating camera motion and intrinsics from casual videos is a core challenge in computer vision. Traditional bundle-adjustment based methods, such as SfM and SLAM, struggle to perform reliably on ar...
arxiv.org
April 23, 2025 at 3:52 PM
ArXiV: arxiv.org/abs/2503.23282
Code and models: github.com/Brummi/anycam
Project page: fwmb.github.io/anycam/
Code and models: github.com/Brummi/anycam
Project page: fwmb.github.io/anycam/