OmniHorizon: In-the-Wild Outdoors Depth and Normal Estimation from Synthetic Omnidirectional Dataset

no code implementations • 9 Dec 2022 • Jay Bhanushali, PRANEETH CHAKRAVARTHULA, Manivannan Muniyandi

Finally, we demonstrate in-the-wild depth and normal estimation on real-world images with UBotNet trained purely on our OmniHorizon dataset, showing the promise of proposed dataset and network for scene understanding.

Autonomous Driving Scene Understanding

VisTaNet: Attention Guided Deep Fusion for Surface Roughness Classification

no code implementations • 18 Sep 2022 • Prasanna Kumar Routray, Aditya Sanjiv Kanade, Jay Bhanushali, Manivannan Muniyandi

Our study shows that analogous to human texture perception, the proposed model chooses a weighted combination of the two modalities (visual and tactile), thus resulting in higher surface roughness classification accuracy; and it chooses to maximize the weightage of the tactile modality where the visual modality fails and vice-versa.

Classification