2 citations · 2 across the 4 of their papers we have counts for
5 papers
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
Paul Engstler, Iro Laina, Christian Rupprecht +1
We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D…
SynCity: Training-Free Generation of 3D Worlds
Paul Engstler, Aleksandar Shtedritski, Iro Laina +2
We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision…
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
Paul Engstler, Andrea Vedaldi, Iro Laina +1
3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area gener…
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht +1
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and…
Interpretable Vertebral Fracture Diagnosis
Paul Engstler, Matthias Keicher, David Schinz +11
Do black-box neural network models learn clinically relevant features for fracture diagnosis? The answer not only establishes reliability quenches scientific curiosity but also lea…