Instructions for oral presentations

Each oral paper presentation is assigned 12 minutes plus 3 minutes for questions and change of speaker. Please ensure that you won't speak for more than 12 minutes. We expect that you will bring your own laptop. There will be a standard HDMI cable to connect laptops. Please bring the right dongle to connect your laptop with HDMI. To avoid technical trouble during the session, all speakers must test their laptop before the session. Don't wait until the last minute to allow enough time for finding a solution in case there will be a problem. All oral presentations also have an additional poster presentation.  

Instructions for poster presentations

The poster boards are A0 portrait format (width: 84.1cm, height: 118.9cm). We will provide pins for mounting them. Please hang up your poster some time between the previous poster session and your poster session and remove it immediately after your poster session to allow people from the next session to hang up their poster. You find the number of your poster board in the PDF linked in the program for the respective poster session. 

For nectar track posters from a previous conference, we have assigned two poster boards placed next to each other, which allows for wider posters. However, the stability of your poster will be limited if the boards are placed too far apart. Also keep in mind that the person on the other side might have a different poster width. Therefore, if your poster from the previous conference is wider than 2 meters, we recommend printing a new poster that fits the A0 portrait format.  

Accepted Papers

The following papers that have been accepted to GCPR 2025. Congratulations to all the respective authors! See you soon at GCPR 2025 in Freiburg.

EVCS: A Benchmark for Fine-Grained Electric Vehicle Charging Station Detection
Chen, Lin; Südbeck, Sönke; Riggers, Christoph; Geib, Tobias; Cordes, Kai; Broszio, Hellward

MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices
Hojjat, Ali; Haberer, Janek; Landsiedel, Olaf

NaT-ReX: Naturalness Assessment with Transformer-Based Reliable Explainability
Emam, Ahmed; Farag, Mohamed; Russwurm, Marc; Roscher, Ribana

subCellSAM: Zero-Shot (Sub-)Cellular Segmentation for Hit Validation in Drug Discovery
Hanimann, Jacob; Siegismund, Daniel; Wieser, Mario; Steigele, Stephan

Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation
Carrion, Dustin; Roth, Stefan; Schaub-Meyer, Simone

Common Data Properties Limit Object-Attribute Binding in CLIP
Guring, Bijay; Hoffmann, David; Brox, Thomas

MT-Occ: Single-View 3D Occupancy Prediction via Multi-Task Distillation
Li, Zhi; Aljundi, Rahaf; Reino, Daniel; Schiele, Bernt

SegSLR: Promptable Video Segmentation for Isolated Sign Language Recognition
Schreiber, Sven; Sarhan, Noha; Frintrop, Simone; Wilms, Christian

synth-dacl: Does Synthetic Defect Data Enhance Segmentation Accuracy and Robustness for Real-World Bridge Inspections?
Flotzinger, Johannes; Deuser, Fabian; Jaziri, Achref ; Neumann, Heiko; Oswald, Norbert; Ramesh, Visvanathan ; Braml, Thomas

Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation
Dreissig, Mariella; Ruehle, Simon; Piewak, Florian; Boedecker, Joschka

VisualChef: Generating Visual Aids in Cooking via Mask Inpainting
Kuzyk, Oleh; Li, Zuoyue; Pollefeys, Marc; Wang, Xi

FedPCE: Federated Personalized Client Embeddings for Post-training Knowledge Distillation
Hansel, Soma; Kobler, Erich; Effland, Alexander

CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometry
Xie, Jingchao; Dhaouadi, Oussema; Chen, Weirong; Meier, Johannes; Kaiser, Jacques; Cremers, Daniel

Video Object Segmentation-aware Audio Generation
Viertola, Ilpo; Iashin, Vladimir; Rahtu, Esa

Object Risk Estimation for Autonomous Driving Safety
Khan, Abdul Hannan; Shafiq, Syed; van Elst, Ludger; Dengel, Andreas

Rethinking Semi-supervised Segmentation Beyond Accuracy: Robustness and Reliability
Landgraf, Steven; Hillemann, Markus; Ulrich, Markus

A Cascaded Dilated Convolution Approach for Mpox Lesion Classification
Deshmukh, Ayush 

Assessing Foundation Models for Mold Colony Detection with Limited Training Data
Pichler, Henrik; Keuper, Janis; Copping, Matthew

Semantic Segmentation of Structural Damage: A Comparative Study of YOLO11 and Encoder-Decoder Networks
Krefft, Lorenz; Hoegner, Ludwig

Structured Universal Adversarial Attacks on Object Detection for Video Sequences
Jacob, Sven; Shao, Weijia; Kasneci, Gjergji

Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
Huang, Yiran; Thede, Lukas; Mancini, Massimiliano; Xu, Wenjia; Akata, Zeynep

Detection of Synthetic Face Images: Accuracy, Robustness, Generalization
Petrželková, Nela; Čech, Jan

HistDiST: Histopathological Diffusion-based Stain Transfer
Grosskopf, Erik; Bundele, Valay; Hosseinzadeh, Mehran; Lensch, Hendrik

Deep Learning-Assisted Dynamic Mode Decomposition for Non-resonant Background Removal in CARS Spectroscopy
Chalain Valapil, Adithya Ashok; Messerschmidt, Carl; Shadaydeh, Maha; Schmitt, Michael; Popp, Jürgen; Denzler, Joachim

Combining Absolute and Semi-Generalized Relative Poses for Visual Localization
Panek, Vojtech; Sattler, Torsten; Kukelova, Zuzana

Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling
Bratulić, Jelena; Mittal, Sudhanshu; Hoffmann, David; Böhm, Samuel; Schirrmeister, Robin; Ball, Tonio; Rupprecht, Christian; Brox, Thomas

Graph Roof Reconstruction with Synthetic Data from Misaligned Labels
Amrullah, Chaikal; Bittner, Ksenia

sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views
Najafli, Eyvaz; Kästingschäfer, Marius; Bernhard, Sebastian; Brox, Thomas; Geiger, Andreas

Can Multitask Learning Enhance Model Explainability?
Najjar, Hiba; Alshbib, Bushra; Dengel, Andreas

Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs
Shojaei Miandashti, Hanieh; Brenner, Claus

γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
Fatima, Mishal; Agnihotri, Shashank; Bock, Marius; Gandikota, Kanchana; Van Laerhoven , Kristof; Moeller, Michael; Keuper, Margret

RadarSeq: A Temporal Vision Framework for User Churn Prediction via Radar Sequence Chart
Najafi, Sina; Sepanj, M.Hadi; Jafari, Fahimeh

Using Knowledge Graphs to harvest datasets for efficient CLIP model training
Ging, Simon; Walter, Sebastian; Bratulić, Jelena; Dienert, Johannes; Bast, Hannah; Brox, Thomas

StorySync: Training-Free Subject Consistency via Region Harmonization
Gaur, Gopalji; Zolfaghari, Mohammadreza; Brox, Thomas

Don’t Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection
Sivaprasad, Sarath; Fritz, Mario

LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation
Wang, Xuqin; Wu, Tao; Zhang, Yanfeng; Liu, Lu; Wang, Dong; Sun, Mingwei; Wang, Yongliang; Zeller, Niclas; Cremers, Daniel

On the Dangers of Bootstrapping Generation for Continual Learning and Beyond
Zverev, Daniil; Koepke, Almut Sophia; Henriques, Joao

Road Obstacle Video Segmentation
Rai, Shyam Nandan; Karthik, Shyamgopal; Georgescu, Iuliana; Caputo, Barbara; Masone, Carlo ; Akata, Zeynep

Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing
Siedel, Georg; Gupta, Ekagra; Shao, Weijia; Vock, Silvia; Morozov, Andrey
 

 

Accepted Papers: Nectar Track

Can We Talk Models Into Seeing the World Differently?
Gavrikov, Paul; Lukasik, Jovita; Jung, Steffen; Geirhos, Robert; Mirza, M. Jehanzeb; Keuper, Margret; Keuper, Janis

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
Schmalwasser, Laines; Penzel, Niklas; Denzler, Joachim; Niebling, Julia

Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models
Venkataramanan, Aishwarya; Bodesheim, Paul; Denzler, Joachim

SEED4D: A Synthetic Ego–Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark
Kästingschäfer, Marius; Gieruc, Theo; Bernhard, Sebastian; Campbell, Dylan; Insafutdinov, Eldar; Najafli, Eyvaz; Brox, Thomas

Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis
Büchner, Tim; Anders, Christoph; Guntinas-Lichius, Orlando; Denzler, Joachim

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
Schoene, Mark; Rahmani, Babak; Kremer, Heiner; Falck, Fabian; Ballani, Hitesh; Gladrow, Jannes

HydraViT: Stacking Heads for a Scalable ViT
Haberer, Janek; Hojjat, Ali; Landsiedel, Olaf

Banded Square Root Matrix Factorization for Differentially Private Model Training
Kalinin, Nikita; Lampert, Christoph

CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series
Stein, Gideon; Shadaydeh, Maha; Blunk, Jan; Penzel, Niklas; Denzler, Joachim

DCBM: Data-Efficient Visual Concept Bottleneck Models
Prasse, Katharina; Knab, Patrick; Marton, Sascha; Bartelt, Christian; Keuper, Margret

Prompt-Tuning SAM: From Generalist to Specialist with only 2048 Parameters and 16 Training Images
Piater, Tristan; Barz, Björn; Freytag, Alexander

FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training
Medi, Tejaswini; Jung, Steffen; Keuper, Margret;

Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching
Roetzer, Paul; Ehm, Viktoria; Cremers, Daniel; Lähner, Zorah; Bernard, Florian

PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?
Spitznagel, Martin; Vaillant, Jan; Keuper, Janis

High-Resolution 3D Shape Matching with Global Optimality and Geometric Consistency
El Amrani, Nafie; Rötzer, Paul; Bernard, Florian

Removing Cost Volumes from Optical Flow Estimators
Kiefhaber, Simon; Roth, Stefan; Schaub-Meyer, Simone

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
Zverev, Egor; Abdelnabi, Sahar; Tabesh, Soroush; Fritz, Mario ; Lampert, Christoph

SOS: Segment Object System for Open-World Instance Segmentation With Object Priors
Wilms, Christian; Rolff, Tim; Hillemann, Maris; Johanson, Robert; Frintrop, Simone

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
Schrodi, Simon; Hoffmann, David; Argus, Max; Fischer, Volker; Brox, Thomas

When and How Does CLIP Enable Domain and Compositional Generalization?
Kempf, Elias; Schrodi, Simon; Argus, Max; Brox, Thomas

Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging
Kahl, Max; Stricker, Sebastian; Hutschenreither, Lisa; Bernard, Florian; Rother, Carsten; Savchynskyy, Bogdan

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
Davtyan, Aram; Dadi, Leello Tadesse; Cevher, Volkan; Favaro, Paolo

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
Davtyan, Aram; Sameni, Sepehr; Ommer, Björn; Favaro, Paolo

MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
Zatsarynna, Olga; Bahrami, Emad; Abu Farha, Yazan; Francesca, Gianpiero; Gall, Juergen

Scene-Centric Unsupervised Panoptic Segmentation
Hahn, Oliver; Reich, Christoph; Araslanov, Nikita; Cremers, Daniel; Rupprecht, Christian; Roth, Stefan

Using Shapley interactions to understand how models use structure
Misra, Diganta

CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation
Sick, Leon; Engel, Dominik; Hartwig, Sebastian; Hermosilla, Pedro; Ropinski, Timo

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
Görgün, Ada; Schiele, Bernt; Fischer, Jonas

AIM: Amending Inherent Interpretability via Self-Supervised Masking
Alshami, Eyad; Agnihotri, Shashank; Schiele, Bernt; Keuper, Margret

The GOOSE Dataset for Perception in Unstructured Environments
Mortimer, Peter; Hagmanns, Raphael; Granero, Miguel; Petereit, Janko; Luettel, Thorsten

DASH: Detection and Assessment of Systematic Hallucinations of VLMs
Augustin, Maximilian; Neuhaus, Yannic; Hein, Matthias

Spatial Reasoning with Denoising Models
Wewer, Christopher; Pogodzinski, Bartlomiej; Schiele, Bernt; Lenssen, Jan

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
Jevtić, Aleksandar; Reich, Christoph; Wimbauer, Felix; Hahn, Oliver; Rupprecht, Christian; Roth, Stefan; Cremers, Daniel

Activation Subspaces for Out-of-Distribution Detection
Zöngür, Barış; Hesse, Robin; Roth, Stefan

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Bousselham, Walid; Boggust, Angie; Chaybouti, Sofian; Strobelt, Hendrik; Kuehne, Hilde

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Arya, Shreyash; Rao, Sukrut; Böhle, Moritz; Schiele, Bernt

VGGSounder: Audio-Visual Evaluations for Foundation Models
Zverev, Daniil; Wiedemer, Thaddäus; Prabhu, Ameya; Bethge, Matthias; Brendel, Wieland; Koepke, A. Sophia

Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
Boettcher, Wolfgang; Hoyer, Lukas; Uenal, Ozan; Lenssen, Jan Eric; Schiele, Bernt

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
Dünkel, Olaf; Wimmer, Thomas; Theobalt, Christian; Rupprecht, Christian; Kortylewski, Adam

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis
Belouadi, Jonas; Ilg, Eddy; Keuper, Margret; Tanaka, Hideki; Utiyama, Masao; Dabre, Raj; Eger, Steffen; Ponzetto, Simone Paolo;

FlowBench: Benchmarking Optical Flow Estimation Methods for Reliability and Generalization
Agnihotri, Shashank; Caspary, Julian; Schwarz, Luca; Gao, Xinyan; Schmalfuss, Jenny; Bruhn, Andres; Keuper, Margret