Person

Sabine Süsstrunk

Related publications (241)

Exploiting the Signal-Leak Bias in Diffusion Models

Sabine Süsstrunk, Radhakrishna Achanta, Mahmut Sami Arpa, Martin Nicolas Everaert, Athanasios Fitsios

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

2024

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Sabine Süsstrunk, Tong Zhang, Yufan Ren

The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize perscene parameters and therefore lack ...

2024

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Sabine Süsstrunk, Yufan Ren, Peter Arpad Grönquist, Alessio Verardo, Qingyi He

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

2024

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Yi Wu

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

2024

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Bahar Aydemir, Ludo Hoffstetter

Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider t ...

2023

, , ,

Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control over the synthesis p ...

2023

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Yulun Jiang, Chen Liu, Zhuoyi Huang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023

Vision Transformer Adapters for Generalizable Multitask Learning

Sabine Süsstrunk, Mathieu Salzmann, Deblina Bhattacharjee

We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf vision transformer backbone, our adapters can simultaneously solve mu ...

2023

Dense Multitask Learning to Reconfigure Comics

Sabine Süsstrunk, Mathieu Salzmann, Deblina Bhattacharjee

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comic panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narrativ ...

IEEE2023

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Marilyne Andersen, Sabine Süsstrunk, Caroline Karmann, Bahar Aydemir, Kynthia Chamilothori, Seungryong Kim

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

2023

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Yulun Jiang, Chen Liu, Zhuoyi Huang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023