Search Results for author: Marko Mihajlovic

Found 14 papers, 12 papers with code

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

1 code implementation10 Nov 2024 Yutong Chen, Marko Mihajlovic, Xiyi Chen, Yiming Wang, Sergey Prokudin, Siyu Tang

To our knowledge, this is the first successful application of point transformers directly on 3DGS sets, surpassing the limitations of previous multi-scene training methods, which could handle only a restricted number of input views during inference.

3DGS Novel View Synthesis

FreSh: Frequency Shifting for Accelerated Neural Representation Learning

1 code implementation7 Oct 2024 Adam Kania, Marko Mihajlovic, Sergey Prokudin, Jacek Tabor, Przemysław Spurek

Implicit Neural Representations (INRs) have recently gained attention as a powerful approach for continuously representing signals such as images, videos, and 3D shapes using multilayer perceptrons (MLPs).

Representation Learning

RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering

no code implementations30 Sep 2024 Deheng Zhang, Jingyu Wang, Shaofei Wang, Marko Mihajlovic, Sergey Prokudin, Hendrik P. A. Lensch, Siyu Tang

Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.

Inverse Rendering

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

1 code implementation17 Sep 2024 Marko Mihajlovic, Sergey Prokudin, Siyu Tang, Robert Maier, Federica Bogo, Tony Tung, Edmond Boyer

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics.

3DGS 4D reconstruction

Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories

no code implementations CVPR 2024 Yan Zhang, Sergey Prokudin, Marko Mihajlovic, Qianli Ma, Siyu Tang

By observing a set of point trajectories, we aim to learn an implicit motion field parameterized by a neural network to predict the movement of novel points within the same domain, without relying on any data-driven or scene-specific priors.

Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation

1 code implementation CVPR 2024 Xiyi Chen, Marko Mihajlovic, Shaofei Wang, Sergey Prokudin, Siyu Tang

To the best of our knowledge, our proposed framework is the first diffusion model to enable the creation of fully 3D-consistent, animatable, and photorealistic human avatars from a single image of an unseen subject; extensive quantitative and qualitative evaluations demonstrate the advantages of our approach over existing state-of-the-art avatar creation models on both novel view and novel expression synthesis tasks.

Novel View Synthesis

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

1 code implementation CVPR 2024 Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang

In this paper, we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS).

3DGS Image Generation

ResFields: Residual Neural Fields for Spatiotemporal Signals

1 code implementation6 Sep 2023 Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang

Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or radiance fields (NeRFs), via a single multi-layer perceptron (MLP).

4D reconstruction NeRF +1

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

1 code implementation10 May 2022 Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang, Shunsuke Saito

In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views.

3D Face Reconstruction 3D Human Reconstruction +2

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

1 code implementation NeurIPS 2021 Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang

In contrast, we propose an approach that can quickly generate realistic clothed human avatars, represented as controllable neural SDFs, given only monocular depth images.

Meta-Learning

LEAP: Learning Articulated Occupancy of People

1 code implementation CVPR 2021 Marko Mihajlovic, Yan Zhang, Michael J. Black, Siyu Tang

Substantial progress has been made on modeling rigid 3D objects using deep implicit representations.

DeepSurfels: Learning Online Appearance Fusion

1 code implementation CVPR 2021 Marko Mihajlovic, Silvan Weder, Marc Pollefeys, Martin R. Oswald

We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information.

Finding the most similar textual documents using Case-Based Reasoning

1 code implementation1 Nov 2019 Marko Mihajlovic, Ning Xiong

In 2016, the new similarity TS-SS metric is proposed, which showed state-of-the-art results in the field of textual mining for unsupervised learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.