2.3k citations · 7.5k across the 162 of their papers we have counts for
12 papers · 2 filters
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos +6
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high…
LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels
Jonathan Schmidt, Qadeer Khan, Daniel Cremers
Deep learning models for self-driving cars require a diverse training dataset to manage critical driving scenarios on public roads safely. This includes having data from divergent…
SIGMA: Scale-Invariant Global Sparse Shape Matching
Maolin Gao, Paul Roetzer, Marvin Eisenberger +4
We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for highly non-rigid shapes. To this end, we introduce a projected Lapl…
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations
Lu Sang, Abhishek Saroha, Maolin Gao +1
Neural implicit representations have become a popular choice for modeling surfaces due to their adaptability in resolution and support for complex topology. While previous works ha…
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
Dominik Muhle, Lukas Koestler, Krishna Murthy Jatavallabhula +1
We propose a differentiable nonlinear least squares framework to account for uncertainty in relative pose estimation from feature correspondences. Specifically, we introduce a symm…
Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes
George Eskandar, Youssef Farag, Tarun Yenamandra +3
A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success,…
Non-Separable Multi-Dimensional Network Flows for Visual Computing
Viktoria Ehm, Daniel Cremers, Florian Bernard
Flows in networks (or graphs) play a significant role in numerous computer vision tasks. The scalar-valued edges in these graphs often lead to a loss of information and thereby to…
Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks
Olaf Wysocki, Yan Xia, Magdalena Wysocki +4
Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise s…
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…
Semidefinite Relaxations for Robust Multiview Triangulation
Linus Härenstam-Nielsen, Niclas Zeller, Daniel Cremers
We propose an approach based on convex relaxations for certifiably optimal robust multiview triangulation. To this end, we extend existing relaxation approaches to non-robust multi…
Behind the Scenes: Density Fields for Single View Reconstruction
Felix Wimbauer, Nan Yang, Christian Rupprecht +1
Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only…
4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions
Patrick Wenzel, Nan Yang, Rui Wang +2
In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The p…