Torben Peters — accepted AI-conference papers

2024

TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation

Nikolai Kalischek*, Torben Peters, Jan Dirk Wegner, Konrad Schindler

ECCV 2024poster

"Probabilistic denoising diffusion models (DDMs) have set a new standard for 2D image generation. Extending DDMs for 3D content creation is an active field of research. Here, we propose TetraDiffusion, a diffusion model that operates on a tetrahedral partitioning of 3D space to enable efficient, hig…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2023

BiasBed - Rigorous Texture Bias Evaluation

Nikolai Kalischek, Rodrigo Caye Daudt, Torben Peters, Reinhard Furrer, Jan D. Wegner, Konrad Schindler

CVPR 2023poster

The well-documented presence of texture bias in modern convolutional neural networks has led to a plethora of algorithms that promote an emphasis on shape cues, often to support generalization to new domains. Yet, common datasets, benchmarks and general model selection strategies are missing, and th…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗