Marko Mihajlovic
I am a PhD student in the VLG group at ETH Zurich since September 2020. 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.
I was a research intern at Meta Reality Labs, hosted by Michael Zollhoefer. I obtained my Master's degree at ETH where I conducted research at CVG.
01/2024: SplatFields is accepted at ECCV 2024!
02/2024: Three papers accepted at CVPR 2024!
01/2024: ResFields is accepted at ICLR 2024 as a spotlight paper!
07/2022: Our KeypointNeRF is accepted at ECCV 2022!
03/2022: Our COAP is accepted at CVPR 2022!
09/2021: Joined Meta Reality Labs as a research intern (hosted by Michael Zollhoefer).
03/2021: Two papers accepted at CVPR 2021 (LEAP, DeepSurfels)!
09/2020: Joined VLG as a PhD student (supervisor Siyu Tang).
09/2020: Completed a two-year Master program at the Instituate for Visual Computing (supervisor Marc Pollefeys).
SplatFields regularizes 3D gaussian splats for sparse 3D and 4D reconstruction.
Morphable diffusion enables consistent controllable novel view synthesis of humans from a single image.
Given a monocular video, 3DGS-Avatar learns a clothed human avatars with short training time and interactive rendering frame rate.
How to infer scene dynamics from sparse point trajectory observations? We show a simple yet effective solution using a spatiotemporal MLP with carefully designed regularizations. No need for scene-specific priors.
ResField layers incorporates time-dependent weights into MLPs to effectively represent complex temporal signals.
KeypointNeRF is a generalizable neural radiance field for virtual avatars. Given as input 2-3 images, KeypointNeRF generates volumetric radiance representation that can be rendered from novel views.
COAP is a novel neural implicit representation for articulated human bodies that provides an efficient mechanism for modeling self-contact and interactions with the environment.
Generalizable and controllable neural signed distance fields (SDFs) that represent clothed humans from monocular depth observations.
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.
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.