activity
20172026
most citedSelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera

76 citations · 207 across the 72 of their papers we have counts for

collaborators
Showing 2020Show all

14 papers · 1 filter

cs.CV2020

D-NeRF: Neural Radiance Fields for Dynamic Scenes

Albert Pumarola, Enric Corona, Gerard Pons-Moll +1

Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a s…

cs.CV2020★ 76 cited

SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera

Denis Tome, Thiemo Alldieck, Patrick Peluse +4

We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device.…

cs.CV2020★ 31 cited

Neural Unsigned Distance Fields for Implicit Function Learning

Julian Chibane, Aymen Mir, Gerard Pons-Moll

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Ne…

cs.CV2020★ 5 cited

SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results

Alexandre Saint, Anis Kacem, Kseniya Cherenkova +7

The SHApe Recovery from Partial textured 3D scans challenge, SHARP 2020, is the first edition of a challenge fostering and benchmarking methods for recovering complete textured 3D…

cs.CV2020

LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt +1

We address the problem of fitting 3D human models to 3D scans of dressed humans. Classical methods optimize both the data-to-model correspondences and the human model parameters (p…

cs.CV2020

Implicit Feature Networks for Texture Completion from Partial 3D Data

Julian Chibane, Gerard Pons-Moll

Prior work to infer 3D texture use either texture atlases, which require uv-mappings and hence have discontinuities, or colored voxels, which are memory inefficient and limited in…