activity
20172019
most citedJoint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs

13 citations · 13 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CV2019

EMPNet: Neural Localisation and Mapping Using Embedded Memory Points

Gil Avraham, Yan Zuo, Thanuja Dharmasiri +1

Continuously estimating an agent's state space and a representation of its surroundings has proven vital towards full autonomy. A shared common ground among systems which successfu…

cs.RO2019

Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation

Sourav Garg, Madhu Babu, Thanuja Dharmasiri +5

Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change. Parti…

cs.CV2018

Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations

Vladimir Nekrasov, Thanuja Dharmasiri, Andrew Spek +3

Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most…

cs.CV2018

CReaM: Condensed Real-time Models for Depth Prediction using Convolutional Neural Networks

Andrew Spek, Thanuja Dharmasiri, Tom Drummond

Since the resurgence of CNNs the robotic vision community has developed a range of algorithms that perform classification, semantic segmentation and structure prediction (depths, n…

cs.CV2018

ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs

Thanuja Dharmasiri, Andrew Spek, Tom Drummond

Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure fr…

cs.CV2018

Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors

Chamara Saroj Weerasekera, Thanuja Dharmasiri, Ravi Garg +2

We present ``just-in-time reconstruction" as real-time image-guided inpainting of a map with arbitrary scale and sparsity to generate a fully dense depth map for the image. In part…