Login
Abhishek Saroha
PhD StudentTechnical University of MunichSchool of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany
Tel: +49-89-289-17784
Fax: +49-89-289-17757
Office: 02.09.053
Mail: Abhishek.Saroha@in.tum.de
Please also see my LinkedIn and my Twitter account.
I am looking for motivated and talented students to work on the topics related, but not limited to, 3D/4D reconstruction, Gaussian Splatting, shape analysis, generative modelling and geometric deep learning. If you are, interested please contact me directly via email and highlight your relevant academic experience and programming skills. Additionally, please include a CV and a recent transcript. Some basic prerequisites for the same are:
- Solid foundation in math
- Proficiency in Python, with experience in PyTorch/Tensorflow
- Have attended at least one related CV course(incl. seminar and lab course).
Publications
Export as PDF, XML, TEX or BIB
Preprints
2025
[] 
ZDySS – Zero-Shot Dynamic Scene Stylization using Gaussian Splatting , In arXiv preprint arXiv:2501.03875, 2025.
2022
[] 
Implicit Shape Completion via Adversarial Shape Priors , In arXiv preprint arXiv:2204.10060, 2022.
Conference and Workshop Papers
2025
[] 
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction , In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025. ([project page])
2024
[] 
DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting , In European Conference on Computer Vision (ECCV), 2024.
[] 
Gaussian Splatting in Style , In German Conference on Pattern Recognition (GCPR), 2024.
[] 
Transferability for Graph Convolutional Networks , In ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling, 2024.
Outstanding Extended Abstract [] 
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations , In ECCV workshop: wild in 3D, 2024. ([project page])
2023
[] 
ResolvNet: A Graph Convolutional Network with multi-scale Consistency , In NeurIPS 2023 Workshop: New Frontiers in Graph Learning, 2023.
Oral Presentation
