Baptiste Angles
YOU?
Author Swipe
View article: FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction
FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction Open
Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without test-time optimization is feasible using deep neural networks, showing remarkable promise and high efficiency. H…
View article: LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses
LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses Open
Dense 3D reconstruction from RGB images traditionally assumes static camera pose estimates. This assumption has endured, even as recent works have increasingly focused on real-time methods for mobile devices. However, the assumption of a f…
View article: Optimizing Through Learned Errors for Accurate Sports Field Registration
Optimizing Through Learned Errors for Accurate Sports Field Registration Open
We propose an optimization-based framework to register sports field templates onto broadcast videos. For accurate registration we go beyond the prevalent feed-forward paradigm. Instead, we propose to train a deep network that regresses the…
View article: VIPER: Volume Invariant Position-based Elastic Rods
VIPER: Volume Invariant Position-based Elastic Rods Open
We extend the formulation of position-based rods to include elastic volumetric deformations. We achieve this by introducing an additional degree of freedom per vertex -- isotropic scale (and its velocity). Including scale enriches the spac…
View article: MIST: Multiple Instance Spatial Transformer Networks
MIST: Multiple Instance Spatial Transformer Networks Open
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extrac…
View article: MIST: Multiple Instance Spatial Transformer Network
MIST: Multiple Instance Spatial Transformer Network Open
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extrac…
View article: Sketch-based implicit blending
Sketch-based implicit blending Open
Implicit models can be combined by using composition operators; functions that determine the resulting shape. Recently, gradient-based composition operators have been used to express a variety of behaviours including smooth transitions, sh…