3 papers
cs.CV2026
Differential pose optimization in descriptor space -- Combining Geometric and Photometric Methods for Motion Estimation
Andreas L. Teigen, Annette Stahl, Rudolf Mester
One of the fundamental problems in computer vision is the two-frame relative pose optimization problem. Primarily, two different kinds of error values are used: photometric error a…
cs.CV2023
Removing Adverse Volumetric Effects From Trained Neural Radiance Fields
Andreas L. Teigen, Mauhing Yip, Victor P. Hamran +3
While the use of neural radiance fields (NeRFs) in different challenging settings has been explored, only very recently have there been any contributions that focus on the use of N…
cs.CV2023
RGB-D Mapping and Tracking in a Plenoxel Radiance Field
Andreas L. Teigen, Yeonsoo Park, Annette Stahl +1
The widespread adoption of Neural Radiance Fields (NeRFs) have ensured significant advances in the domain of novel view synthesis in recent years. These models capture a volumetric…