AIConfPaper
← Search

Suprosanna Shit

12 accepted papers

2026

Beyond Uniformity: Regularizing Implicit Neural Representations through a Lipschitz Lens

Julian McGinnis, Suprosanna Shit, Florian A. Hölzl, Paul Friedrich, Paul Büschl, Vasiliki Sideri-Lampretsa +5
ICLR 2026poster

Implicit Neural Representations (INRs) have shown great promise in solving inverse problems, but their lack of inherent regularization often leads to a trade-off between expressiveness and smoothness. While Lipschitz continuity presents a principled form of implicit regularization, it is often appli…

Cited by 0Source ↗Scholar ↗
2026

Optimizing Rank for High-Fidelity Implicit Neural Representations

Julian McGinnis, Florian A. Hölzl, Suprosanna Shit, Florentin Bieder, Paul Friedrich, Mark Mühlau +3
ICML 2026poster

Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-frequency content. This has directed research efforts towards architectural interventions, such as coordinate embeddings or specialized activation functions…

Cited by 0Source ↗Scholar ↗
2025

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud, Dong Yang, Pengfei Guo +4
NeurIPS 2025poster

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditi…

Cited by 0Source ↗code ↗Scholar ↗
2025

Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling

Michal Balcerak, Tamaz Amiranashvili, Antonio Terpin, Suprosanna Shit, Lea Bogensperger, Sebastian Kaltenbach +2
NeurIPS 2025poster

Current state-of-the-art generative models map noise to data distributions by matching flows or scores. A key limitation of these models is their inability to readily integrate available partial observations and additional priors. In contrast, energy-based models (EBMs) address this by incorporating…

Cited by 0Source ↗Scholar ↗
2025

vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation

Bastian Wittmann, Yannick Wattenberg, Tamaz Amiranashvili, Suprosanna Shit, Bjoern Menze
CVPR 2025poster

Segmenting 3D blood vessels is a critical yet challenging task in medical image analysis. This is due to significant imaging modality-specific variations in artifacts, vascular patterns and scales, signal-to-noise ratios, and background tissues. These variations, along with domain gaps arising from…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

A Skeletonization Algorithm for Gradient-Based Optimization

Martin J. Menten, Johannes C. Paetzold, Veronika A. Zimmer, Suprosanna Shit, Ivan Ezhov, Robbie Holland +3
ICCV 2023poster

The skeleton of a digital image is a compact representation of its topology, geometry, and scale. It has utility in many computer vision applications, such as image description, segmentation, and registration. However, skeletonization has only seen limited use in contemporary deep learning solutions…

Cited by 15PDF ↗code ↗Scholar ↗
2023

InstanceFormer: An Online Video Instance Segmentation Framework

Rajat Koner, Tanveer Hannan, Suprosanna Shit, Sahand Sharifzadeh, Matthias Schubert, Thomas Seidl +1
AAAI 2023technical

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-li…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2023

Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes

Nico Daniel Stucki, Johannes C. Paetzold, Suprosanna Shit, bjoern menze, Ulrich Bauer
ICML 2023poster

Segmentation models predominantly optimize pixel-overlap-based loss, an objective that is actually inadequate for many segmentation tasks. In recent years, their limitations fueled a growing interest in topology-aware methods, which aim to recover the topology of the segmented structures. However, s…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2022

Relationformer: A Unified Framework for Image-to-Graph Generation

Suprosanna Shit, Rajat Koner, Bastian Wittmann, Johannes Paetzold, Ivan Ezhov, Hongwei Li +5
ECCV 2022poster

"A comprehensive representation of an image requires understanding objects and their mutual relationship, especially in image-to-graph generation, e.g., road network extraction, blood-vessel network extraction, or scene graph generation. Traditionally, image-to-graph generation is addressed with a t…

Cited by 69Source ↗PDF ↗code ↗Scholar ↗
2021

Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience

Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar +6
NeurIPS 2021poster

Biological neural networks define the brain function and intelligence of humans and other mammals, and form ultra-large, spatial, structured graphs. Their neuronal organization is closely interconnected with the spatial organization of the brain's microvasculature, which supplies oxygen to the neuro…

Cited by 28Source ↗Scholar ↗
2021

clDice - A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

Suprosanna Shit, Johannes C. Paetzold, Anjany Sekuboyina, Ivan Ezhov, Alexander Unger, Andrey Zhylka +3
CVPR 2021poster

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particularly preserving connectedness: in the case of vascular networks, missing a connecte…

Cited by 327PDF ↗code ↗Scholar ↗
2018

Phasesplit: A Variable Splitting Framework for Phase Retrieval

Subhadip Mukherjee, Suprosanna Shit, Chandra Sekhar Seelamantula
ICASSP 2018accepted

We develop two techniques based on alternating minimization and alternating directions method of multipliers for phase retrieval (PR) by employing a variable-splitting approach in a maximum likelihood estimation framework. This leads to an additional equality constraint, which is incorporated in the…

Cited by 0Source ↗Scholar ↗