3 papers
cs.CV2025
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
Andreea Ardelean, Mert Ãzer, Bernhard Egger
Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of…
cs.CV2024
ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting
Takuma Nishimura, Andreea Dogaru, Martin Oeggerli +1
Scanning Electron Microscopes (SEMs) are widely renowned for their ability to analyze the surface structures of microscopic objects, offering the capability to capture highly detai…
cs.CV2024
RANRAC: Robust Neural Scene Representations via Random Ray Consensus
Benno Buschmann, Andreea Dogaru, Elmar Eisemann +2
Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges…