7 citations · 9 across the 8 of their papers we have counts for
8 papers
AnyUp: Universal Feature Upsampling
Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona +4
We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsample…
Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
Olaf Dünkel, Thomas Wimmer, Christian Theobalt +2
Finding correspondences between semantically similar points across images and object instances is one of the everlasting challenges in computer vision. While large pre-trained visi…
MEt3R: Measuring Multi-View Consistency in Generated Images
Mohammad Asim, Christopher Wewer, Thomas Wimmer +2
We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inf…
Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes
Thomas Wimmer, Michael Oechsle, Michael Niemeyer +1
State-of-the-art novel view synthesis methods achieve impressive results for multi-view captures of static 3D scenes. However, the reconstructed scenes still lack "liveliness," a k…
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features
Thomas Wimmer, Peter Wonka, Maks Ovsjanikov
With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose…
Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training
Miriam Anschütz, Joshua Oehms, Thomas Wimmer +2
Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these…
Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution
Hoai Nam Dang, Vladimir Golkov, Thomas Wimmer +3
Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN). In turbo spin echo sequences (T…
Scale-Equivariant Deep Learning for 3D Data
Thomas Wimmer, Vladimir Golkov, Hoai Nam Dang +3
The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional opera…