Search Results for author: Sara Vicente

Found 10 papers, 4 papers with code

AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

no code implementations CVPR 2024 Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel Brostow, Michael Firman, Sara Vicente

We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches and our strong geometric baseline for the task of plane estimation.

Learning Structured Gaussians to Approximate Deep Ensembles

no code implementations CVPR 2022 Ivor J. A. Simpson, Sara Vicente, Neill D. F. Campbell

Similarly to distillation approaches, our single network is trained to maximise the probability of samples from pre-trained probabilistic models, in this work we use a fixed ensemble of networks.

Monocular Depth Estimation

Training VAEs Under Structured Residuals

2 code implementations3 Apr 2018 Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson

This paper demonstrates a novel scheme to incorporate a structured Gaussian likelihood prediction network within the VAE that allows the residual correlations to be modeled.

Structured Uncertainty Prediction Networks

2 code implementations CVPR 2018 Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.

Image Denoising

Lifting Object Detection Datasets into 3D

no code implementations22 Mar 2015 Joao Carreira, Sara Vicente, Lourdes Agapito, Jorge Batista

In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image.

3D Reconstruction Object +4

Reconstructing PASCAL VOC

no code implementations CVPR 2014 Sara Vicente, Joao Carreira, Lourdes Agapito, Jorge Batista

We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations.


Cannot find the paper you are looking for? You can Submit a new open access paper.