3 papers
cs.CV2026
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
Ruxiao Duan, Erin Hong, Dongxu Zhao +3
Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view i…
cs.CV2024
Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field
Liuyue Xie, Jiancong Guo, Laszlo A. Jeni +4
Recent extended reality headsets and field robots have adopted covers to protect the front-facing cameras from environmental hazards and falls. The surface irregularities on the co…
cs.CV2024
FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding
Xingxing Zuo, Pouya Samangouei, Yunwen Zhou +2
Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this en…