Geometric structure based and regularized depth estimation from 360 indoor imagery
Motivated by the correlation between the depth and the geometric structure of a 360 indoor
image, we propose a novel learning-based depth estimation framework that leverages the …
image, we propose a novel learning-based depth estimation framework that leverages the …
Directed ray distance functions for 3d scene reconstruction
We present an approach for full 3D scene reconstruction from a single unseen image. We
trained on dataset of realistic non-watertight scans of scenes. Our approach uses a …
trained on dataset of realistic non-watertight scans of scenes. Our approach uses a …
What's on the other side? a single-view 3d scene reconstruction
Robots have limited perception capabilities when observing a new scene. When the objects
on the scene are registered from a single perspective, only partial information about the …
on the scene are registered from a single perspective, only partial information about the …
Geometric-driven structure recovery from a single omnidirectional image based on planar depth map learning
M Meng, L Xiao, Z Zhou - Neural Computing and Applications, 2023 - Springer
Scene structure recovery is a crucial process for assisting scene reconstruction and
understanding by extracting vital scene structure information and has been widely used in …
understanding by extracting vital scene structure information and has been widely used in …