Bjorn Ommer

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation CVPR 2026 EDGS: Eliminating Densification for Efficient Convergence of 3DGS CVPR 2026 Envisioning the Future, One Step at a Time CVPR 2026 Guiding Token-Sparse Diffusion Models CVPR 2026 Learning Long-term Motion Embeddings for Efficient Kinematics Generation CVPR 2026 Probabilistic Precipitation Nowcasting with Rectified Flow Transformers CVPR 2026 CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation AAAI 2025 CleanDIFT: Diffusion Features without Noise CVPR 2025 Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions CVPR 2025 DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching AAAI 2025 Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment CVPR 2025 Distillation of Diffusion Features for Semantic Correspondence WACV 2025 Does VLM Classification Benefit from LLM Description Semantics? AAAI 2025 Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis CVPR 2025 SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models ICCV 2025 Stochastic Interpolants for Revealing Stylistic Flows across the History of Art ICCV 2025 TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025 What If: Understanding Motion Through Sparse Interactions ICCV 2025 CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models ECCV 2024 Flow Matching for Conditional Text Generation in a Few Sampling Steps EACL 2024 FMBoost: Boosting Latent Diffusion with Flow Matching ECCV 2024 Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation NeurIPS 2024 WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians ECCV 2024 ZigMa: A DiT-style Zigzag Mamba Diffusion Model ECCV 2024 Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning CVPR 2023 High-Resolution Image Synthesis With Latent Diffusion Models CVPR 2022 Retrieval-Augmented Diffusion Models NeurIPS 2022 Behavior-Driven Synthesis of Human Dynamics CVPR 2021 Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning NeurIPS 2021 Geometry-Free View Synthesis: Transformers and No 3D Priors ICCV 2021 ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis NeurIPS 2021 iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis ICCV 2021 Learning Multi-Scale Photo Exposure Correction CVPR 2021 Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes CVPR 2021 Shape or Texture: Understanding Discriminative Features in CNNs ICLR 2021 Simultaneous Similarity-based Self-Distillation for Deep Metric Learning ICML 2021 SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation ICCV 2021 Stochastic Image-to-Video Synthesis Using cINNs CVPR 2021 Taming Transformers for High-Resolution Image Synthesis CVPR 2021 Understanding Object Dynamics for Interactive Image-to-Video Synthesis CVPR 2021 A Disentangling Invertible Interpretation Network for Explaining Latent Representations CVPR 2020 DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning ECCV 2020 Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs ECCV 2020 Network-to-Network Translation with Conditional Invertible Neural Networks NeurIPS 2020 PADS: Policy-Adapted Sampling for Visual Similarity Learning CVPR 2020 Revisiting Training Strategies and Generalization Performance in Deep Metric Learning ICML 2020 Unsupervised Magnification of Posture Deviations Across Subjects CVPR 2020 A Content Transformation Block for Image Style Transfer CVPR 2019 Content and Style Disentanglement for Artistic Style Transfer ICCV 2019 Divide and Conquer the Embedding Space for Metric Learning CVPR 2019 MIC: Mining Interclass Characteristics for Improved Metric Learning ICCV 2019 Unsupervised Part-Based Disentangling of Object Shape and Appearance CVPR 2019 Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis ICCV 2019 A Style-Aware Content Loss for Real-time HD Style Transfer ECCV 2018 A Variational U-Net for Conditional Appearance and Shape Generation CVPR 2018 Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning ECCV 2018 Deep Semantic Feature Matching CVPR 2017 Deep Unsupervised Similarity Learning Using Partially Ordered Sets CVPR 2017 LSTM Self-Supervision for Detailed Behavior Analysis CVPR 2017 Self-Supervised Learning of Pose Embeddings From Spatiotemporal Relations in Videos ICCV 2017 Unsupervised Video Understanding by Reconciliation of Posture Similarities ICCV 2017 CliqueCNN: Deep Unsupervised Exemplar Learning NeurIPS 2016 Per-Sample Kernel Adaptation for Visual Recognition and Grouping ICCV 2015 Regularizing Max-Margin Exemplars by Reconstruction and Generative Models CVPR 2015 Randomized Max-Margin Compositions for Visual Recognition CVPR 2014 Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity NeurIPS 2012