VLG | Computer Vision and Learning Group

Basic Information

I am a PhD student at ETH Zurich supervised by Prof. Dr. Siyu Tang since September 2020. Previously, I obtained my Master's degree at ETH as a part of the Direct Doctorate in Computer Science.

My research lies at the intersection of computer vision, machine learning, and computer graphics. I am particularly interested in realistic reconstruction of the 3D world around us and understanding how we, as humans, interact with the environment.

Social

Publications

ResFields: Residual Neural Fields for Spatiotemporal Signals

Conference: International Conference on Learning Representations (ICLR 2024) spotlight presentation

Authors:Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang
ResField layers incorporates time-dependent weights into MLPs to effectively represent complex temporal signals.

Project PDF Code BibTeX

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

Conference: European Conference on Computer Vision (ECCV 2022)

Authors:Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang, Shunsuke Saito
KeypointNeRF is a generalizable neural radiance field for virtual avatars.

Project PDF Code BibTeX

COAP: Compositional Articulated Occupancy of People

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2022)

Authors:Marko Mihajlovic , Shunsuke Saito , Aayush Bansal , Michael Zollhoefer and Siyu Tang
COAP is a novel neural implicit representation for articulated human bodies that provides an efficient mechanism for modeling self-contacts and interactions with 3D environments.

Project PDF Code BibTeX

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

Conference: Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)

Authors:Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang
MetaAvatar is meta-learned model that represents generalizable and controllable neural signed distance fields (SDFs) for clothed humans. It can be fast fine-tuned to represent unseen subjects given as few as 8 monocular depth images.

Project PDF Code BibTeX

DeepSurfels: Learning Online Appearance Fusion

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2021)

Authors:Marko Mihajlovic, Silvan Weder, Marc Pollefeys, Martin R. Oswald
DeepSurfels is a novel 3D representation for geometry and appearance information that combines planar surface primitives with voxel grid representation for improved scalability and rendering quality.

Project PDF Code BibTeX

LEAP: Learning Articulated Occupancy of People

Conference: Conference on Computer Vision and Pattern Recognition (CVPR 2021)

Authors:Marko Mihajlovic, Yan Zhang, Michael J. Black and Siyu Tang
LEAP is a neural network architecture for representing volumetric animatable human bodies. It follows traditional human body modeling techniques and leverages a statistical human prior to generalize to unseen humans.

Project PDF Code BibTeX

Basic Information

Social

Publications

ResFields: Residual Neural Fields for Spatiotemporal Signals

Authors:Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang ResField layers incorporates time-dependent weights into MLPs to effectively represent complex temporal signals.

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

Authors:Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang, Shunsuke Saito KeypointNeRF is a generalizable neural radiance field for virtual avatars.

COAP: Compositional Articulated Occupancy of People

Authors:Marko Mihajlovic , Shunsuke Saito , Aayush Bansal , Michael Zollhoefer and Siyu Tang COAP is a novel neural implicit representation for articulated human bodies that provides an efficient mechanism for modeling self-contacts and interactions with 3D environments.

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

DeepSurfels: Learning Online Appearance Fusion

Authors:Marko Mihajlovic, Silvan Weder, Marc Pollefeys, Martin R. Oswald DeepSurfels is a novel 3D representation for geometry and appearance information that combines planar surface primitives with voxel grid representation for improved scalability and rendering quality.

LEAP: Learning Articulated Occupancy of People

Authors:Marko Mihajlovic, Yan Zhang, Michael J. Black and Siyu Tang LEAP is a neural network architecture for representing volumetric animatable human bodies. It follows traditional human body modeling techniques and leverages a statistical human prior to generalize to unseen humans.

Authors:Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang
ResField layers incorporates time-dependent weights into MLPs to effectively represent complex temporal signals.

Authors:Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang, Shunsuke Saito
KeypointNeRF is a generalizable neural radiance field for virtual avatars.

Authors:Marko Mihajlovic , Shunsuke Saito , Aayush Bansal , Michael Zollhoefer and Siyu Tang
COAP is a novel neural implicit representation for articulated human bodies that provides an efficient mechanism for modeling self-contacts and interactions with 3D environments.

Authors:Marko Mihajlovic, Silvan Weder, Marc Pollefeys, Martin R. Oswald
DeepSurfels is a novel 3D representation for geometry and appearance information that combines planar surface primitives with voxel grid representation for improved scalability and rendering quality.

Authors:Marko Mihajlovic, Yan Zhang, Michael J. Black and Siyu Tang
LEAP is a neural network architecture for representing volumetric animatable human bodies. It follows traditional human body modeling techniques and leverages a statistical human prior to generalize to unseen humans.