Picture for Magnus Oskarsson

Magnus Oskarsson

Learning Multi-Target TDOA Features for Sound Event Localization and Detection

Add code
Aug 30, 2024
Viaarxiv icon

wav2pos: Sound Source Localization using Masked Autoencoders

Add code
Aug 28, 2024
Viaarxiv icon

Robust and Accurate Cylinder Triangulation

Add code
Dec 05, 2022
Viaarxiv icon

Extending GCC-PHAT using Shift Equivariant Neural Networks

Add code
Aug 09, 2022
Figure 1 for Extending GCC-PHAT using Shift Equivariant Neural Networks
Figure 2 for Extending GCC-PHAT using Shift Equivariant Neural Networks
Figure 3 for Extending GCC-PHAT using Shift Equivariant Neural Networks
Figure 4 for Extending GCC-PHAT using Shift Equivariant Neural Networks
Viaarxiv icon

Multiple Offsets Multilateration: a new paradigm for sensor network calibration with unsynchronized reference nodes

Add code
May 23, 2022
Figure 1 for Multiple Offsets Multilateration: a new paradigm for sensor network calibration with unsynchronized reference nodes
Figure 2 for Multiple Offsets Multilateration: a new paradigm for sensor network calibration with unsynchronized reference nodes
Viaarxiv icon

Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition

Add code
Apr 08, 2022
Figure 1 for Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
Figure 2 for Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
Figure 3 for Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
Figure 4 for Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
Viaarxiv icon

Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation

Add code
Dec 11, 2020
Figure 1 for Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation
Figure 2 for Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation
Figure 3 for Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation
Figure 4 for Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation
Viaarxiv icon

A novel joint points and silhouette-based method to estimate 3D human pose and shape

Add code
Dec 11, 2020
Figure 1 for A novel joint points and silhouette-based method to estimate 3D human pose and shape
Figure 2 for A novel joint points and silhouette-based method to estimate 3D human pose and shape
Figure 3 for A novel joint points and silhouette-based method to estimate 3D human pose and shape
Figure 4 for A novel joint points and silhouette-based method to estimate 3D human pose and shape
Viaarxiv icon

Deep Ordinal Regression with Label Diversity

Add code
Jun 29, 2020
Figure 1 for Deep Ordinal Regression with Label Diversity
Figure 2 for Deep Ordinal Regression with Label Diversity
Figure 3 for Deep Ordinal Regression with Label Diversity
Figure 4 for Deep Ordinal Regression with Label Diversity
Viaarxiv icon

A fast minimal solver for absolute camera pose with unknown focal length and radial distortion from four planar points

Add code
Jun 05, 2018
Figure 1 for A fast minimal solver for absolute camera pose with unknown focal length and radial distortion from four planar points
Viaarxiv icon