Björn Ommer

papers

22,437

total citations

papers (20)

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

CVPR 2025arXiv

citations

CleanDIFT: Diffusion Features without Noise

CVPR 2025arXiv

citations

Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs

ECCV 2020arXiv

citations

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

CVPR 2025arXiv

citations

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

ICCV 2025arXiv

citations

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

CVPR 2025arXiv

citations

Does VLM Classification Benefit from LLM Description Semantics?

AAAI 2025arXiv

citations

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation

AAAI 2025arXiv

citations

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

ICCV 2025arXiv

citations

Stochastic Interpolants for Revealing Stylistic Flows across the History of Art

ICCV 2025

citations

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

ICCV 2021

citations

Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning

CVPR 2023

citations

Retrieval-Augmented Diffusion Models

NEURIPS 2022

citations

What If: Understanding Motion Through Sparse Interactions

ICCV 2025

citations

Björn Ommer

papers (20)

High-Resolution Image Synthesis With Latent Diffusion Models

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

Geometry-Free View Synthesis: Transformers and No 3D Priors

DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning

iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

CleanDIFT: Diffusion Features without Noise

Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

Does VLM Classification Benefit from LLM Description Semantics?

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Stochastic Interpolants for Revealing Stylistic Flows across the History of Art

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning

Retrieval-Augmented Diffusion Models

What If: Understanding Motion Through Sparse Interactions

papers (20)

High-Resolution Image Synthesis With Latent Diffusion Models

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

Geometry-Free View Synthesis: Transformers and No 3D Priors

DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning

iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

CleanDIFT: Diffusion Features without Noise

Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

Does VLM Classification Benefit from LLM Description Semantics?

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Stochastic Interpolants for Revealing Stylistic Flows across the History of Art

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning

Retrieval-Augmented Diffusion Models

What If: Understanding Motion Through Sparse Interactions