Search Results for author: Samuel Rota Bulò

Found 31 papers, 9 papers with code

Mapillary Planet-Scale Depth Dataset

no code implementations ECCV 2020 Manuel López Antequera, Pau Gargallo, Markus Hofinger, Samuel Rota Bulò, Yubin Kuang, Peter Kontschieder

Learning-based methods produce remarkable results on single image depth tasks when trained on well-established benchmarks, however, there is a large gap from these benchmarks to real-world performance that is usually obscured by the common practice of fine-tuning on the target dataset.

VR-NeRF: High-Fidelity Virtualized Walkable Spaces

no code implementations5 Nov 2023 Linning Xu, Vasu Agrawal, William Laney, Tony Garcia, Aayush Bansal, Changil Kim, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Aljaž Božič, Dahua Lin, Michael Zollhöfer, Christian Richardt

We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields.

GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields

no code implementations9 Jun 2023 Barbara Roessle, Norman Müller, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Matthias Nießner

Neural Radiance Fields (NeRF) have shown impressive novel view synthesis results; nonetheless, even thorough recordings yield imperfections in reconstructions, for instance due to poorly observed areas or minor lighting changes.

3D Scene Reconstruction Novel View Synthesis

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

no code implementations CVPR 2023 Norman Müller, Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Matthias Nießner

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models.

Denoising

AutoRF: Learning 3D Object Radiance Fields from Single View Observations

no code implementations CVPR 2022 Norman Müller, Andrea Simonelli, Lorenzo Porzi, Samuel Rota Bulò, Matthias Nießner, Peter Kontschieder

We introduce AutoRF - a new approach for learning neural 3D object representations where each object in the training set is observed by only a single view.

Novel View Synthesis Object

Dense Prediction with Attentive Feature Aggregation

no code implementations1 Nov 2021 Yung-Hsu Yang, Thomas E. Huang, Min Sun, Samuel Rota Bulò, Peter Kontschieder, Fisher Yu

Our experiments show consistent and significant improvements on challenging semantic segmentation benchmarks, including Cityscapes, BDD100K, and Mapillary Vistas, at negligible computational and parameter overhead.

Boundary Detection Semantic Segmentation

Inferring Latent Domains for Unsupervised Deep Domain Adaptation

no code implementations25 Mar 2021 Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci

Most deep UDA approaches operate in a single-source, single-target scenario, i. e. they assume that the source and the target samples arise from a single distribution.

Unsupervised Domain Adaptation

Weakly Supervised Multi-Object Tracking and Segmentation

no code implementations3 Jan 2021 Idoia Ruiz, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Joan Serrat

We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i. e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.

Instance Segmentation Multi-Object Tracking +7

Improving Panoptic Segmentation at All Scales

no code implementations CVPR 2021 Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder

Crop-based training strategies decouple training resolution from GPU memory consumption, allowing the use of large-capacity panoptic segmentation networks on multi-megapixel images.

Panoptic Segmentation Segmentation

Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?

no code implementations ICCV 2021 Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Elisa Ricci

Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split.

Monocular 3D Object Detection object-detection

DSLib: An open source library for the dominant set clustering method

1 code implementation15 Oct 2020 Sebastiano Vascon, Samuel Rota Bulò, Vittorio Murino, Marcello Pelillo

This package provides an implementation of the original DS clustering algorithm since no code has been officially released yet, together with a still growing collection of methods and variants related to it.

Clustering Graph Matching

Boosting Deep Open World Recognition by Clustering

no code implementations20 Apr 2020 Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo

While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training set.

Clustering Incremental Learning +1

Modeling the Background for Incremental Learning in Semantic Segmentation

1 code implementation CVPR 2020 Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo

Current strategies fail on this task because they do not consider a peculiar aspect of semantic segmentation: since each training step provides annotation only for a subset of all possible classes, pixels of the background class (i. e. pixels that do not belong to any other classes) exhibit a semantic distribution shift.

Continual Learning Disjoint 10-1 +9

Improving Optical Flow on a Pyramid Level

no code implementations ECCV 2020 Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi, Arno Knapitsch, Thomas Pock, Peter Kontschieder

In this work we review the coarse-to-fine spatial feature pyramid concept, which is used in state-of-the-art optical flow estimation networks to make exploration of the pixel flow search space computationally tractable and efficient.

Blocking Optical Flow Estimation

Towards Generalization Across Depth for Monocular 3D Object Detection

no code implementations ECCV 2020 Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Elisa Ricci, Peter Kontschieder

While expensive LiDAR and stereo camera rigs have enabled the development of successful 3D object detection methods, monocular RGB-only approaches lag much behind.

Monocular 3D Object Detection Object +1

Learning Multi-Object Tracking and Segmentation from Automatic Annotations

no code implementations CVPR 2020 Lorenzo Porzi, Markus Hofinger, Idoia Ruiz, Joan Serrat, Samuel Rota Bulò, Peter Kontschieder

Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1. 9%/+7. 5% on cars/pedestrians), and MOTSNet improves by +4. 1% over previously best methods on the MOTSChallenge dataset.

Instance Segmentation Multi-Object Tracking +4

Seamless Scene Segmentation

5 code implementations CVPR 2019 Lorenzo Porzi, Samuel Rota Bulò, Aleksander Colovic, Peter Kontschieder

In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results.

Panoptic Segmentation Scene Segmentation +1

AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs

1 code implementation CVPR 2019 Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci

The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines.

Domain Adaptation

Is Data Clustering in Adversarial Settings Secure?

no code implementations25 Nov 2018 Battista Biggio, Ignazio Pillai, Samuel Rota Bulò, Davide Ariu, Marcello Pelillo, Fabio Roli

In this work we propose a general framework that allows one to identify potential attacks against clustering algorithms, and to evaluate their impact, by making specific assumptions on the adversary's goal, knowledge of the attacked system, and capabilities of manipulating the input data.

Clustering

Best sources forward: domain generalization through source-specific nets

no code implementations15 Jun 2018 Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci

A long standing problem in visual object categorization is the ability of algorithms to generalize across different testing conditions.

Domain Generalization Object Categorization

Robust Place Categorization with Deep Domain Generalization

1 code implementation30 May 2018 Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci

Our method develops from the intuition that, given a set of different classification models associated to known domains (e. g. corresponding to multiple environments, robots), the best model for a new sample in the novel domain can be computed directly at test time by optimally combining the known models.

Domain Generalization General Classification

Boosting Domain Adaptation by Discovering Latent Domains

2 code implementations CVPR 2018 Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci

Our approach is based on the introduction of two main components, which can be embedded into any existing CNN architecture: (i) a side branch that automatically computes the assignment of a source sample to a latent domain and (ii) novel layers that exploit domain membership information to appropriately align the distribution of the CNN internal feature representations to a reference distribution.

Domain Adaptation

AutoDIAL: Automatic DomaIn Alignment Layers

2 code implementations ICCV 2017 Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò

Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one.

Domain Adaptation

Loss Max-Pooling for Semantic Image Segmentation

no code implementations CVPR 2017 Samuel Rota Bulò, Gerhard Neuhold, Peter Kontschieder

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation.

Image Segmentation Segmentation +1

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation

no code implementations21 Feb 2017 Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò

The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains.

Unsupervised Domain Adaptation

Randomized Prediction Games for Adversarial Machine Learning

no code implementations3 Sep 2016 Samuel Rota Bulò, Battista Biggio, Ignazio Pillai, Marcello Pelillo, Fabio Roli

In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e. g., malware code is typically obfuscated using random strings or byte sequences to hide known exploits.

BIG-bench Machine Learning General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.