activity
20182022
most citedFast video object segmentation with Spatio-Temporal GANs

7 citations · 15 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2022

Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation

Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo +2

The recovery of multi-person 3D poses from a single RGB image is a severely ill-conditioned problem due to the inherent 2D-3D depth ambiguity, inter-person occlusions, and body tru…

cs.CV20222 cited

Single-view 3D Body and Cloth Reconstruction under Complex Poses

Nicolas Ugrinovic, Albert Pumarola, Alberto Sanfeliu +1

Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn t…

cs.CV2019

Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds

Victor Vaquero, Kai Fischer, Francesc Moreno-Noguer +2

Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odomet…

cs.CV2019

3DPeople: Modeling the Geometry of Dressed Humans

Albert Pumarola, Jordi Sanchez, Gary P. T. Choi +2

Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothi…

cs.CV20197 cited

Fast video object segmentation with Spatio-Temporal GANs

Sergi Caelles, Albert Pumarola, Francesc Moreno-Noguer +2

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models…

cs.CV2018

Geometry-Aware Network for Non-Rigid Shape Prediction from a Single View

Albert Pumarola, Antonio Agudo, Lorenzo Porzi +3

We propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the su…