3 papers
cs.CV2024
Space3D-Bench: Spatial 3D Question Answering Benchmark
Emilia Szymanska, Mihai Dusmanu, Jan-Willem Buurlage +2
Answering questions about the spatial properties of the environment poses challenges for existing language and vision foundation models due to a lack of understanding of the 3D wor…
cs.CV2024
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References
Lukas Bösiger, Mihai Dusmanu, Marc Pollefeys +1
Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training au…
cs.CV2024
EgoGen: An Egocentric Synthetic Data Generator
Gen Li, Kaifeng Zhao, Siwei Zhang +5
Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to t…