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.
no code implementations • 9 Apr 2024 • Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder
In this paper, we address the limitations of Adaptive Density Control (ADC) in 3D Gaussian Splatting (3DGS), a scene representation method achieving high-quality, photorealistic results for novel view synthesis.
no code implementations • 5 Dec 2023 • Haithem Turki, Vasu Agrawal, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Deva Ramanan, Michael Zollhöfer, Christian Richardt
Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render.
no code implementations • 5 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.
no code implementations • 9 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.
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.
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.
no code implementations • 1 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.
no code implementations • 25 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.
no code implementations • 3 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.
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.
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.
1 code implementation • 15 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.
no code implementations • 20 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.
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.
Ranked #3 on Domain 11-5 on Cityscapes
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.
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.
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.
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.
Ranked #2 on Panoptic Segmentation on KITTI Panoptic Segmentation
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.
no code implementations • 25 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.
no code implementations • 15 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.
Ranked #112 on Domain Generalization on PACS
1 code implementation • 30 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.
no code implementations • 28 May 2018 • Massimiliano Mancini, Elisa Ricci, Barbara Caputo, Samuel Rota Bulò
Visual recognition algorithms are required today to exhibit adaptive abilities.
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.
2 code implementations • CVPR 2018 • Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder
Also, we demonstrate how frequently used checkpointing approaches can be made computationally as efficient as InPlace-ABN.
Ranked #3 on Semantic Segmentation on KITTI Semantic Segmentation
1 code implementation • MM '17 Proceedings of the 25th ACM international conference on Multimedia 2017 • Alejandro Hernandez Ruiz, Lorenzo Porzi, Samuel Rota Bulò, Francesc Moreno-Noguer
In this paper we are interested in recognizing human actions from sequences of 3D skeleton data.
Ranked #90 on Skeleton Based Action Recognition on NTU RGB+D
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.
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.
no code implementations • 25 Feb 2017 • Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo
This paper presents an approach for semantic place categorization using data obtained from RGB cameras.
no code implementations • 21 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.
no code implementations • 3 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.