Florian Barthel

I am a PHD candidate at the Humboldt University of Berlin (Chair for Visual Computing) and a research assistant at Fraunhofer HHI (Vision and Imaging Technologies Group). My work focuses on synthesizing realistic 3D humans using state-of-the-art methods like 3D Gaussian Splatting, NeRF and 3D-aware Generative Adversarial Networks.

Publications

	CVPRW 2024: Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks In this work, we present a novel approach that combines the high rendering quality of NeRF-based 3D-aware Generative Adversarial Networks with the flexibility and computational advantages of 3DGS. By training a decoder that maps implicit NeRF representations to explicit 3D Gaussian Splatting attributes, we can integrate the representational diversity and quality of 3D GANs into the ecosystem of 3D Gaussian Splatting for the first time.	Paper Project Page Code
	Compact 3D Scene Representation via Self-Organizing Gaussian Grids In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering.	Paper Project Page Code
	VISAPP 2024: Multi-view Inversion for 3D-aware Generative Adversarial Networks Our method builds on existing state-of-the-art 3D GAN inversion techniques to allow for consistent and simultaneous inversion of multiple views of the same subject. We employ a multi-latent extension to handle inconsistencies present in dynamic face videos to re-synthesize consistent 3D representations from the sequence.	Paper Project Page Code
	ICMR 2024: Creating Sorted Grid Layouts with Gradient-based Optimization In this paper, we present a novel method for grid-based sorting that exploits gradient optimization for the first time. We introduce a novel loss function that balances two opposing goals: ensuring the generation of a "valid" permutation matrix, and optimizing the arrangement on the grid to reflect the similarity between vectors, inspired by metrics that assess the quality of sorted grids.
	ICCV 2023: Haystack: a panoptic scene graph dataset to evaluate rare predicate classes Haystack is a panoptic scene graph dataset that in contrast to existing scene graph datasets, includes explicit negative relation annotations. Negative relation annotations are important during evaluation, because they can drastically reduce label noise that occurs when relations are missed by annotators. During sampling, prior scene graph datasets will introduce some false negative labels, wheras Haystack guarantees that all negative relations are correct (assuming a perfect annotator).	Paper Project Page Code
	SN Computer Science 2022: Controlling 3D objects in 2D image synthesis In this work, we propose a method that enforces explicit control over various attributes during the image generation process in a generative adversarial net. We propose a semi-supervised learning procedure that allows us to use a quantized approximation of object orientation for learning continuous object rotations. As a result, among many other attributes, our proposed method allows us to control object orientation in scenes that are rendered according to our specifications.	Paper

Projects

Gaussian Viewer

This interactive viewer allows to display 3D Gaussian Splatting objects stored as .ply files or as compressed objects from Compact 3D Scene Representation via Self-Organizing Gaussian Grids. The viewer is fully written in python, which makes development and debugging very simple.

GitHub

ERWIN (Student Project)

Erwin is a single-player puzzle game with co-op components. The idea is to play levels that would normally only be solvable in pairs, alone with the help of a rewind mechanism. To do this, the player first starts a level alone and plans ahead, then rewinds time and solves the level cooperatively with his past. The level design makes use of familiar co-op elements, such as buttons that can be activated, portable crates, jumping plates and much more. In total, the game contains 16 different levels.

itch.io

Thesis

2022 Master Thesis: Conditional Rendering of 3D Objects from 2D Images using Deep Generative Neural Networks

In this thesis, we will present a method that allows to conditionally synthesize photorealistic 3D-like 360° views of cars using multi-labeled 2D data.

PDF

2020 Bachelor Thesis: An Extensive Study of the StyleGAN Architecture for Deep Image Synthesis

This thesis analyzes the StyleGAN architecture, developed by the Nvidia research group Tero Karras et al. In the context of an ablation study, each component of the StyleGAN will be analyzed separately.

PDF