activity
20182025
most citedTensor-based Emotion Editing in the StyleGAN Latent Space

7 citations · 9 across the 5 of their papers we have counts for

collaborators

8 papers

cs.SD2025

From Sound to Sight: Towards AI-authored Music Videos

Leo Vitasovic, Stella Graßhof, Agnes Mercedes Kloft +6

Conventional music visualisation systems rely on handcrafted ad hoc transformations of shapes and colours that offer only limited expressiveness. We propose two novel pipelines for…

cs.CV2023★ 1 cited

Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models

René Haas, Inbar Huberman-Spiegelglas, Rotem Mulayoff +3

Denoising Diffusion Models (DDMs) have emerged as a strong competitor to Generative Adversarial Networks (GANs). However, despite their widespread use in image synthesis and editin…

cs.CV2022

Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion

René Haas, Stella Graßhof, Sami S. Brandt

In this paper, we present an approach for combining non-rigid structure-from-motion (NRSfM) with deep generative models,and propose an efficient framework for discovering trajector…

cs.CV2022★ 7 cited

Tensor-based Emotion Editing in the StyleGAN Latent Space

René Haas, Stella Graßhof, Sami S. Brandt

In this paper, we use a tensor model based on the Higher-Order Singular Value Decomposition (HOSVD) to discover semantic directions in Generative Adversarial Networks. This is achi…

cs.CV2021

Tensor-based Subspace Factorization for StyleGAN

René Haas, Stella Graßhof, Sami Sebastian Brandt

In this paper, we propose GAN a tensor-based method for modeling the latent space of generative models. The objective is to identify semantic directions in latent space. To this…

cs.CV2019★ 1 cited

Non-Rigid Structure-From-Motion by Rank-One Basis Shapes

Sami S. Brandt, Hanno Ackermann

In this paper, we show that the affine, non-rigid structure-from-motion problem can be solved by rank-one, thus degenerate, basis shapes. It is a natural reformulation of the class…