69 citations · 626 across the 60 of their papers we have counts for
77 papers
Adversarial Appearance Learning in Augmented Cityscapes for Pedestrian Recognition in Autonomous Driving
Artem Savkin, Thomas Lapotre, Kevin Strauss +2
In the autonomous driving area synthetic data is crucial for cover specific traffic scenarios which autonomous vehicle must handle. This data commonly introduces domain gap between…
Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
Zhiying Leng, Shun-Cheng Wu, Mahdi Saleh +6
Reconstructing both objects and hands in 3D from a single RGB image is complex. Existing methods rely on manually defined hand-object constraints in Euclidean space, leading to sub…
SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs
Guangyao Zhai, Xiaoni Cai, Dianye Huang +5
Object rearrangement is pivotal in robotic-environment interactions, representing a significant capability in embodied AI. In this paper, we present SG-Bot, a novel rearrangement f…
3D Compositional Zero-shot Learning with DeCompositional Consensus
Muhammad Ferjad Naeem, Evin Pınar Örnek, Yongqin Xian +2
Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. To…
Neural Fields in Visual Computing and Beyond
Yiheng Xie, Towaki Takikawa, Shunsuke Saito +7
Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physica…
SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
Yan Di, Fabian Manhardt, Gu Wang +3
Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (e.g. the 3D rotation and translation) in a cluttered environment from a single RGB image is a challenging p…
R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes
Stefano Gasperini, Patrick Koch, Vinzenz Dallabetta +3
While self-supervised monocular depth estimation in driving scenarios has achieved comparable performance to supervised approaches, violations of the static world assumption can st…
Attention-based Adversarial Appearance Learning of Augmented Pedestrians
Kevin Strauss, Artem Savkin, Federico Tombari
Synthetic data became already an essential component of machine learning-based perception in the field of autonomous driving. Yet it still cannot replace real data completely due t…
On the Practicality of Deterministic Epistemic Uncertainty
Janis Postels, Mattia Segu, Tao Sun +4
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Net…
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
Farid Yagubbayli, Yida Wang, Alessio Tonioni +1
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them. Th…
Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction
Janis Postels, Mengya Liu, Riccardo Spezialetti +2
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. How…
KLIEP-based Density Ratio Estimation for Semantically Consistent Synthetic to Real Images Adaptation in Urban Traffic Scenes
Artem Savkin, Federico Tombari
Synthetic data has been applied in many deep learning based computer vision tasks. Limited performance of algorithms trained solely on synthetic data has been approached with domai…
SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching
Hongzhi Du, Yanyan Li, Yanbiao Sun +2
The cost aggregation strategy shows a crucial role in learning-based stereo matching tasks, where 3D convolutional filters obtain state of the art but require intensive computation…
TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
Margarita Grinvald, Federico Tombari, Roland Siegwart +1
The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction…
Content Disentanglement for Semantically Consistent Synthetic-to-Real Domain Adaptation
Mert Keser, Artem Savkin, Federico Tombari
Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthet…
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Shun-Cheng Wu, Johanna Wald, Keisuke Tateno +2
Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks. This work proposes a method to incrementally build up semanti…
ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames
Raza Yunus, Yanyan Li, Federico Tombari
In this paper, a robust RGB-D SLAM system is proposed to utilize the structural information in indoor scenes, allowing for accurate tracking and efficient dense mapping on a CPU. P…
Unsupervised Novel View Synthesis from a Single Image
Pierluigi Zama Ramirez, Diego Martin Arroyo, Alessio Tonioni +1
Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time lim…
Learning Graph Embeddings for Compositional Zero-shot Learning
Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari +1
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) i…
The Hidden Uncertainty in a Neural Networks Activations
Janis Postels, Hermann Blum, Yannick Strümpler +4
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution…
Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis
Ruixuan Yu, Xin Wei, Federico Tombari +1
In this paper we propose a rotation-invariant deep network for point clouds analysis. Point-based deep networks are commonly designed to recognize roughly aligned 3D shapes based o…
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
Riccardo Spezialetti, David Joseph Tan, Alessio Tonioni +2
Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning. Most approaches regress the…
3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer
Mattia Segu, Margarita Grinvald, Roland Siegwart +1
Transferring the style from one image onto another is a popular and widely studied task in computer vision. Yet, style transfer in the 3D setting remains a largely unexplored probl…
Batch Normalization Embeddings for Deep Domain Generalization
Mattia Segu, Alessio Tonioni, Federico Tombari
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models…