288 citations · 351 across the 18 of their papers we have counts for
23 papers · 1 filter
DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving
Yung-Hsu Yang, Luigi Piccinelli, Siyuan Li +8
Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance…
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
Luca Barsellotti, Martin Sundermeyer, Mattia Segu +5
Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computation…
MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning
Mattia Segu, Marta Tintore Gazulla, Yongqin Xian +2
Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object d…
Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation
Silvio Mazzucco, Carl Persson, Mattia Segu +4
We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher…
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
Yung-Hsu Yang, Luigi Piccinelli, Mattia Segu +6
Monocular 3D object detection is valuable for various applications such as robotics and AR/VR. Existing methods are confined to closed-set settings, where the training and testing…
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos +8
Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on no…
UniK3D: Universal Camera Monocular 3D Estimation
Luigi Piccinelli, Christos Sakaridis, Mattia Segu +4
Monocular 3D estimation is crucial for visual perception. However, current methods fall short by relying on oversimplified assumptions, such as pinhole camera models or rectified i…
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
Luigi Piccinelli, Christos Sakaridis, Yung-Hsu Yang +4
Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is c…
Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking
Mattia Segu, Luigi Piccinelli, Siyuan Li +3
Multiple object tracking in complex scenarios - such as coordinated dance performances, team sports, or dynamic animal groups - presents unique challenges. In these settings, objec…
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs
Mattia Segu, Luigi Piccinelli, Siyuan Li +3
The supervision of state-of-the-art multiple object tracking (MOT) methods requires enormous annotation efforts to provide bounding boxes for all frames of all videos, and instance…
SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking
Siyuan Li, Lei Ke, Yung-Hsu Yang +4
Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on p…
Matching Anything by Segmenting Anything
Siyuan Li, Lei Ke, Martin Danelljan +4
The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predom…
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
Rui Li, Tobias Fischer, Mattia Segu +3
Recovering the 3D scene geometry from a single view is a fundamental yet ill-posed problem in computer vision. While classical depth estimation methods infer only a 2.5D scene repr…
UniDepth: Universal Monocular Metric Depth Estimation
Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis +4
Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is c…
COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking
Zhizheng Liu, Mattia Segu, Fisher Yu
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the sc…
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
Mattia Segu, Bernt Schiele, Fisher Yu
Multiple object tracking (MOT) is a fundamental component of perception systems for autonomous driving, and its robustness to unseen conditions is a requirement to avoid life-criti…
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts
Qi Fan, Mattia Segu, Yu-Wing Tai +4
Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary subst…
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Tao Sun, Mattia Segu, Janis Postels +5
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, howeve…
Generative Cooperative Learning for Unsupervised Video Anomaly Detection
Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan +3
Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings. However, unsupervised video anomaly detection methods are quite spars…
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…
Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
Mattia Segu, Federico Pirovano, Gianmario Fumagalli +1
Most state-of-the-art methods for action recognition rely only on 2D spatial features encoding appearance, motion or pose. However, 2D data lacks the depth information, which is cr…
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…
A General Framework for Uncertainty Estimation in Deep Learning
Antonio Loquercio, Mattia Segù, Davide Scaramuzza
Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fund…