23 citations · 67 across the 10 of their papers we have counts for
13 papers
Rethinking Classifier-Free Guidance for TI2I Flow Matching
Andreas Floros, Elena Koritska, Teofilo de Campos +4
We study Text-and-Image-to-Image (TI2I) flow matching methods for controllable image editing. In a broader generative modeling context, Classifier-Free Guidance (CFG) is establishe…
ImLoc: Revisiting Visual Localization with Image-based Representation
Xudong Jiang, Fangjinhua Wang, Silvano Galliani +2
Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based,…
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
Xudong Jiang, Fangjinhua Wang, Silvano Galliani +2
Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination chang…
GLACE: Global Local Accelerated Coordinate Encoding
Fangjinhua Wang, Xudong Jiang, Silvano Galliani +2
Scene coordinate regression (SCR) methods are a family of visual localization methods that directly regress 2D-3D matches for camera pose estimation. They are effective in small-sc…
FLoc: Fusion and Filtering for Floorplan Localization
Changan Chen, Rui Wang, Christoph Vogel +1
In this paper we propose an efficient data-driven solution to self-localization within a floorplan. Floorplan data is readily available, long-term persistent and inherently robust…
IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo
Fangjinhua Wang, Silvano Galliani, Christoph Vogel +1
We present IterMVS, a new data-driven method for high-resolution multi-view stereo. We propose a novel GRU-based estimator that encodes pixel-wise probability distributions of dept…
PatchmatchNet: Learned Multi-View Patchmatch Stereo
Fangjinhua Wang, Silvano Galliani, Christoph Vogel +2
We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo. With high computation speed and low memory requirement, Pat…
DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion
Arda Düzçeker, Silvano Galliani, Christoph Vogel +3
We propose an online multi-view depth prediction approach on posed video streams, where the scene geometry information computed in the previous time steps is propagated to the curr…
Self-Supervised Learning for Stereo Reconstruction on Aerial Images
Patrick Knöbelreiter, Christoph Vogel, Thomas Pock
Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation. On the downside, learning these networks requi…
Learning Energy Based Inpainting for Optical Flow
Christoph Vogel, Patrick Knöbelreiter, Thomas Pock
Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze. In this wor…
Variational 3D-PIV with Sparse Descriptors
Katrin Lasinger, Christoph Vogel, Thomas Pock +1
3D Particle Imaging Velocimetry (3D-PIV) aim to recover the flow field in a volume of fluid, which has been seeded with tracer particles and observed from multiple camera viewpoint…
3D Fluid Flow Estimation with Integrated Particle Reconstruction
Katrin Lasinger, Christoph Vogel, Thomas Pock +1
The standard approach to densely reconstruct the motion in a volume of fluid is to inject high-contrast tracer particles and record their motion with multiple high-speed cameras. A…
Semantic 3D Reconstruction with Finite Element Bases
Audrey Richard, Christoph Vogel, Maros Blaha +2
We propose a novel framework for the discretisation of multi-label problems on arbitrary, continuous domains. Our work bridges the gap between general FEM discretisations, and labe…