Shivangi Aneja

I am a PhD candidate at Visual Computing and AI Lab at Technical University of Munich advised by Prof. Matthias Nie├čner. Prior to that, I obtained my Masters degree in Informatics from Technical University of Munich and Bachelors degree in Computer Science from National Institute of Technology, Hamirpur (India). My Master's thesis earned highest honors, and was awarded Best Master Thesis Award at DGOF Conference. During my undergrad, I was awarded gold medal for academic excellence. My PhD research focuses on developing algorithms to generate lifelike and immersive 3D digital humans with expressive capabilities. Additionally, I also develop novel approaches that can thwart the malevolent usage of such generative models.

What's New

Aug, 2023
Rising Stars Scholar 2023, WiGRAPH
Selected as one of the participants for Rising Stars 2023, WiGRAPH co-located with SIGGRAPH 2023 & 2024.
Aug, 2023
ClipFace got accepted to SIGGRAPH 2023
Feb, 2023
COSMOS got accepted to AAAI 2023
Oct, 2022
TAFIM got accepted to ECCV 2022
Sept, 2022
Grand Challenge on Detecting CheapFakes, ACM Multimedia Conference
Co-organized a competition on detecting out-of-context misuse of images in collaboration with Google AI.
Sept, 2021
Grand Challenge on Detecting CheapFakes, ACM MMSys Conference
Co-organized a competition on detecting out-of-context misuse of images in collaboration with Google AI.
Sept, 2021
Best Master Thesis 2021
Awarded Best Master Thesis Award for the academic year 2020-2021 at DGOF Conference for my Master Thesis
Jun, 2021
Apr, 2020
Graduated Masters in Informatics (Magna Cum Laude), TUM
Master Thesis: Generalized Zero and Few-Shot Transfer for Facial Forgery Detection

Research

Shivangi Aneja, Justus Thies, Angela Dai, Matthias Niessner

ClipFace learns a self-supervised generative model for jointly synthesizing geometry and texture leveraging 3D morphable face models guided by text prompts. We can then generate arbitrary face textures as UV maps. The textured mesh can then be manipulated with text guidance to generate diverse set of textures and geometric expressions in 3D.

Shivangi Aneja, Chris Bregler, Matthias Niessner

One of the most prevalent ways to mislead audiences on social media is the use of unaltered images in a new but false context. To address this challenge and support fact-checkers, we propose a new method that automatically detects out-of-context image and text pairs.

Shivangi Aneja, Lev Markhasin, Matthias Niessner

We introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original images to prevent face manipulation by causing the manipulation model to produce a predefined manipulation target. Our generalized model only needs a single forward pass, thus running orders of magnitude faster and allowing for easy integration in image processing stacks, even on resource-constrained devices.

Pranjal Singh Rajput, Shivangi Aneja

We introduce the first large-scale ethnic dataset of over 106K images with 15 different categories for fine-grained classification of Indian ethnic clothes. We gathered a diverse dataset from a large number of Indian e-commerce websites. We hope that our dataset would foster research in the development of several algorithms such as cloth classification, landmark detection, especially for ethnic clothes.

Shivangi Aneja, Matthias Niessner

We propose a new transfer learning approach to address the problem of zero and few-shot transfer in the context of facial forgery detection. To facilitate transfer, we introduce a new mixture model-based loss formulation that learns a multi-modal distribution, with modes corresponding to class categories of the underlying data of the source forgery method.