← Search

Tom Fischer

2 accepted papers

2025

Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes

ICCV 2025poster

Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D inputs, which may not always be available, or employ two-stage…

2024

Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields

ICML 2024poster

Deep learning has revolutionized the field of computer vision by introducing large scale neural networks with millions of parameters. Training these networks requires massive datasets and leads to intransparent models that can fail to generalize. At the other extreme, models designed from partial di…

Cited by 1SourcePDFScholar