Filters








4 Hits in 2.2 sec

ODE-CNN: Omnidirectional Depth Extension Networks [article]

Xinjing Cheng, Peng Wang, Yanqi Zhou, Chenye Guan, Ruigang Yang
2020 arXiv   pre-print
To accurately recover the missing depths, we design an omnidirectional depth extension convolutional neural network(ODE-CNN), in which a spherical feature transform layer(SFTL) is embedded at the end of  ...  Finally, we demonstrate the effectiveness of proposed ODE-CNN over the popular 360D dataset and show that ODE-CNN significantly outperforms (relatively 33 in-depth error) other state-of-the-art (SoTA)  ...  Finally, after properly embed the two proposed modules, we illustrate our whole framework for ominidirectional depth extension (ODE) in Fig. 2 , which is named as ODE-CNN.  ... 
arXiv:2007.01475v1 fatcat:sz6eicbf6vbbnl6z6stockshdm

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation [article]

Yuyan Li, Zhixin Yan, Ye Duan, Liu Ren
2022 arXiv   pre-print
In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular depth estimation.  ...  We conducted extensive experiments and ablation studies to evaluate PanoDepth with both the full pipeline as well as the individual modules in each stage.  ...  Comparing the performance with ODE-CNN [11] on 360D, our approach achieves comparable results while ODE-CNN requires additional depth sensor input.  ... 
arXiv:2202.01323v1 fatcat:nwbb2tiferfm5hmm4x3otphoye

OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion [article]

Yuyan Li, Yuliang Guo, Zhixin Yan, Xinyu Huang, Ye Duan, Liu Ren
2022 arXiv   pre-print
A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion.  ...  Last, we introduce an iterative depth refinement mechanism, to further refine the estimated depth based on the more accurate geometric features.  ...  Note that compared to ODE-CNN [6] which used additional sensor input, our method reduces Abs Rel by 7.9%. Qualitative results of our method can be visualized in Figure 6 .  ... 
arXiv:2203.00838v2 fatcat:qer27pe5rbfjtg62qv2j7hscly

UniFuse: Unidirectional Fusion for 360^∘ Panorama Depth Estimation [article]

Hualie Jiang, Zhe Sheng, Siyu Zhu, Zilong Dong, Rui Huang
2021 arXiv   pre-print
Learning depth from spherical panoramas is becoming a popular research topic because a panorama has a full field-of-view of the environment and provides a relatively complete description of a scene.  ...  More recently, ODE-CNN [25] reduces the 360 • depth estimation problem as an extension problem from the front face depth. Both their experiments are still performed on virtual datasets only.  ...  network to fuse the estimated depth maps from both branches.  ... 
arXiv:2102.03550v1 fatcat:eog2geeu4ffsxlcrhaq5ppmzdm