Research Group Xi Wang
Xi Wang
Dr.
JRG Leader Egocentric Vision
Xi Wang
leads the MCML Junior Research Group ‘Egocentric Vision’ at TU Munich.
Xi Wang and her team conduct cutting-edge research in egocentric vision, focusing on learning from first-person human videos to understand behavior patterns and extract valuable information for potential applications in robotics. Their ongoing projects include 3D reconstruction using Gaussian splitting and multimodal learning with vision-language models. Funded as a BMBF project, the group maintains close ties with MCML and actively seeks collaborations that bridge egocentric vision with other research domains, extending beyond our own focus.
Team members @MCML
PhD Students
Abhishek Saroha
→ Group Xi Wang
Computer Vision & Artificial Intelligence
Dominik Schnaus
→ Group Xi Wang
Computer Vision & Artificial Intelligence
Recent News @MCML
Publications @MCML
2026
[16]
C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
Graph Neural Networks Are Not Continuous Across Graph Resolutions.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
Graph Neural Networks Are Not Continuous Across Graph Resolutions.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
[15]
A. Saroha • H. Zeng • X. Zuo • D. Cremers • X. Wang
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
[14]
H. Zeng • A. Saroha • D. Cremers • X. Wang
GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes.
3DV 2026 - 13th International Conference on 3D Vision. Vancouver, Canada, Mar 20-23, 2026. To be published. Preprint available. URL
GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes.
3DV 2026 - 13th International Conference on 3D Vision. Vancouver, Canada, Mar 20-23, 2026. To be published. Preprint available. URL
[13]
Y. Wang • Y. Miao • W. Zhao • W. Yang • Z. Wang • J. Pajarinen • L. Van Gool • D. P. Paudel • J. Kannala • X. Wang • A. Solin
PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos.
Preprint (Mar. 2026). arXiv GitHub
PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos.
Preprint (Mar. 2026). arXiv GitHub
2025
[12]
O. Kuzyk • Z. Li • M. Pollefeys • X. Wang
VisualChef: Generating Visual Aids in Cooking via Mask Inpainting.
GCPR 2025 - German Conference on Pattern Recognition. Freiburg, Germany, Oct 23-26, 2025. DOI
VisualChef: Generating Visual Aids in Cooking via Mask Inpainting.
GCPR 2025 - German Conference on Pattern Recognition. Freiburg, Germany, Oct 23-26, 2025. DOI
[11]
G. Zhang • S. Qian • X. Wang • D. Cremers
ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association.
Preprint (Sep. 2025). arXiv GitHub
ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association.
Preprint (Sep. 2025). arXiv GitHub
[10]
D. Schnaus • N. Araslanov • D. Cremers
It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data.
CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. DOI GitHub
It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data.
CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. DOI GitHub
[9]
C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
Graph Networks struggle with variable Scale.
ICBINB @ICLR 2025 - Workshop I Can’t Believe It’s Not Better: Challenges in Applied Deep Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
Graph Networks struggle with variable Scale.
ICBINB @ICLR 2025 - Workshop I Can’t Believe It’s Not Better: Challenges in Applied Deep Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
[8]
C. Koke • D. Schnaus • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
On multi-scale Graph Representation Learning.
LMRL @ICLR 2025 - Workshop on Learning Meaningful Representations of Life at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
On multi-scale Graph Representation Learning.
LMRL @ICLR 2025 - Workshop on Learning Meaningful Representations of Life at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
[7]
C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
On Incorporating Scale into Graph Networks.
MLMP @ICLR 2025 - Workshop on Machine Learning Multiscale Processes at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Best Paper Award. URL
On Incorporating Scale into Graph Networks.
MLMP @ICLR 2025 - Workshop on Machine Learning Multiscale Processes at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Best Paper Award. URL
[6]
N. P. A. Vu • A. Saroha • O. Litany • D. Cremers
GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields.
Preprint (Mar. 2025). arXiv
GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields.
Preprint (Mar. 2025). arXiv
[5]
A. Saroha • F. Hofherr • M. Gladkova • C. Curreli • O. Litany • D. Cremers
ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting.
Preprint (Jan. 2025). arXiv
ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting.
Preprint (Jan. 2025). arXiv
2024
[4]
L. Sang • A. Saroha • M. Gao • D. Cremers
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations.
GCPR 2024 - German Conference on Pattern Recognition. Munich, Germany, Oct 10-13, 2024. DOI
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations.
GCPR 2024 - German Conference on Pattern Recognition. Munich, Germany, Oct 10-13, 2024. DOI
[3]
A. Saroha • M. Gladkova • C. Curreli • D. Muhle • T. Yenamandra • D. Cremers
Gaussian Splatting in Style.
GCPR 2024 - German Conference on Pattern Recognition. Munich, Germany, Oct 10-13, 2024. DOI
Gaussian Splatting in Style.
GCPR 2024 - German Conference on Pattern Recognition. Munich, Germany, Oct 10-13, 2024. DOI
[2]
L. Härenstam-Nielsen • L. Sang • A. Saroha • N. Araslanov • D. Cremers
DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI GitHub
DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI GitHub
[1]
L. Sang • M. Gao • A. Saroha • D. Cremers
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations.
Wild3D @ECCV 2024 - Workshop 3D Modeling, Reconstruction, and Generation in the Wild at the 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. URL
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations.
Wild3D @ECCV 2024 - Workshop 3D Modeling, Reconstruction, and Generation in the Wild at the 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. URL
©all images: LMU | TUM
Back to Top
2025-03-14 - Last modified: 2026-07-03