Search

Motivated by efficiency requirements, most anomaly detection and segmentation (AD&S) methods focus on processing low-resolution images, e.g., $224\times 224$ pixels, obtained by downsampling the original input images. In this setting, downsampling is typically applied also to the provided ground-truth defect masks. Yet, as numerous industrial applications demand identification of both large and tiny defects, the above-described protocol may fall short in providing a realistic picture of the actual performance attainable by current methods. Hence, in this work, we introduce a novel benchmark that evaluates methods on the original, high-resolution image and ground-truth masks, focusing on segmentation performance as a function of the size of anomalies. Our benchmark includes a metric that captures robustness with respect to defect size, i.e., the ability of a method to preserve good localization from large anomalies to tiny ones. Furthermore, we introduce an AD&S approach based on a novel Teacher-Student paradigm which relies on two shallow MLPs (the Students) that learn to transfer patch features across the layers of a frozen vision transformer (the Teacher). By means of our benchmark, we evaluate our proposal and other recent AD&S methods on high-resolution inputs containing large and tiny defects. Our proposal features the highest robustness to defect size, runs at the fastest speed, yields state-of-the-art performance on the MVTec AD dataset and state-of-the-art segmentation performance on the VisA dataset.

Multimodal Large Language Models (MLLMs) have demonstrated an excellent understanding of images and 3D data. However, both modalities have shortcomings in holistically capturing the appearance and geometry of objects. Meanwhile, Neural Radiance Fields (NeRFs), which encode information within the weights of a simple Multi-Layer Perceptron (MLP), have emerged as an increasingly widespread modality that simultaneously encodes the geometry and photorealistic appearance of objects. This paper investigates the feasibility and effectiveness of ingesting NeRF into MLLM. We create LLaNA, the first general-purpose NeRF-language assistant capable of performing new tasks such as NeRF captioning and Q\&A. Notably, our method directly processes the weights of the NeRF's MLP to extract information about the represented objects without the need to render images or materialize 3D data structures. Moreover, we build a dataset of NeRFs with text annotations for various NeRF-language tasks with no human intervention. Based on this dataset, we develop a benchmark to evaluate the NeRF understanding capability of our method. Results show that processing NeRF weights performs favourably against extracting 2D or 3D representations from NeRFs., Comment: Under review. Project page: https://andreamaduzzi.github.io/llana/

Neural Radiance Fields (NeRFs) have emerged as a standard framework for representing 3D scenes and objects, introducing a novel data type for information exchange and storage. Concurrently, significant progress has been made in multimodal representation learning for text and image data. This paper explores a novel research direction that aims to connect the NeRF modality with other modalities, similar to established methodologies for images and text. To this end, we propose a simple framework that exploits pre-trained models for NeRF representations alongside multimodal models for text and image processing. Our framework learns a bidirectional mapping between NeRF embeddings and those obtained from corresponding images and text. This mapping unlocks several novel and useful applications, including NeRF zero-shot classification and NeRF retrieval from images or text., Comment: Accepted at CVPRW-INRV 2024

Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD., Comment: Accepted at VAND 2.0, CVPRW 2024

In recent years, Neural Fields (NFs) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D data, NFs offer a solution to the fragmentation and limitations associated with prevalent discrete representations. However, given that NFs are essentially neural networks, it remains unclear whether and how they can be seamlessly integrated into deep learning pipelines for solving downstream tasks. This paper addresses this research problem and introduces nf2vec, a framework capable of generating a compact latent representation for an input NF in a single inference pass. We demonstrate that nf2vec effectively embeds 3D objects represented by the input NFs and showcase how the resulting embeddings can be employed in deep learning pipelines to successfully address various tasks, all while processing exclusively NFs. We test this framework on several NFs used to represent 3D surfaces, such as unsigned/signed distance and occupancy fields. Moreover, we demonstrate the effectiveness of our approach with more complex NFs that encompass both geometry and appearance of 3D objects such as neural radiance fields., Comment: Extended version of the paper "Deep Learning on Implicit Neural Representations of Shapes" that was presented at ICLR 2023. Accepted at TPAMI. arXiv admin note: text overlap with arXiv:2302.05438

The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies. We introduce a novel light and fast framework that learns to map features from one modality to the other on nominal samples. At test time, anomalies are detected by pinpointing inconsistencies between observed and mapped features. Extensive experiments show that our approach achieves state-of-the-art detection and segmentation performance in both the standard and few-shot settings on the MVTec 3D-AD dataset while achieving faster inference and occupying less memory than previous multimodal AD methods. Moreover, we propose a layer-pruning technique to improve memory and time efficiency with a marginal sacrifice in performance., Comment: Accepted at CVPR 2024

Driven by the appealing properties of neural fields for storing and communicating 3D data, the problem of directly processing them to address tasks such as classification and part segmentation has emerged and has been investigated in recent works. Early approaches employ neural fields parameterized by shared networks trained on the whole dataset, achieving good task performance but sacrificing reconstruction quality. To improve the latter, later methods focus on individual neural fields parameterized as large Multi-Layer Perceptrons (MLPs), which are, however, challenging to process due to the high dimensionality of the weight space, intrinsic weight space symmetries, and sensitivity to random initialization. Hence, results turn out significantly inferior to those achieved by processing explicit representations, e.g., point clouds or meshes. In the meantime, hybrid representations, in particular based on tri-planes, have emerged as a more effective and efficient alternative to realize neural fields, but their direct processing has not been investigated yet. In this paper, we show that the tri-plane discrete data structure encodes rich information, which can be effectively processed by standard deep-learning machinery. We define an extensive benchmark covering a diverse set of fields such as occupancy, signed/unsigned distance, and, for the first time, radiance fields. While processing a field with the same reconstruction quality, we achieve task performance far superior to frameworks that process large MLPs and, for the first time, almost on par with architectures handling explicit representations., Comment: Accepted at ICLR 2024

While text-conditional 3D object generation and manipulation have seen rapid progress, the evaluation of coherence between generated 3D shapes and input textual descriptions lacks a clear benchmark. The reason is twofold: a) the low quality of the textual descriptions in the only publicly available dataset of text-shape pairs; b) the limited effectiveness of the metrics used to quantitatively assess such coherence. In this paper, we propose a comprehensive solution that addresses both weaknesses. Firstly, we employ large language models to automatically refine textual descriptions associated with shapes. Secondly, we propose a quantitative metric to assess text-to-shape coherence, through cross-attention mechanisms. To validate our approach, we conduct a user study and compare quantitatively our metric with existing ones. The refined dataset, the new metric and a set of text-shape pairs validated by the user study comprise a novel, fine-grained benchmark that we publicly release to foster research on text-to-shape coherence of text-conditioned 3D generative models. Benchmark available at https://cvlab-unibo.github.io/CrossCoherence-Web/., Comment: ICCV 2023 Workshop "AI for 3D Content Creation", Project page: https://cvlab-unibo.github.io/CrossCoherence-Web/, 26 pages

Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks. We propose a simple pipeline for learning to estimate depth properly for such surfaces with neural networks, without requiring any ground-truth annotation. We unveil how to obtain reliable pseudo labels by in-painting ToM objects in images and processing them with a monocular depth estimation model. These labels can be used to fine-tune existing monocular or stereo networks, to let them learn how to deal with ToM surfaces. Experimental results on the Booster dataset show the dramatic improvements enabled by our remarkably simple proposal., Comment: Accepted at ICCV 2023. Project Page: https://cvlab-unibo.github.io/Depth4ToM

In this paper, we focus on the problem of rendering novel views from a Neural Radiance Field (NeRF) under unobserved light conditions. To this end, we introduce a novel dataset, dubbed ReNe (Relighting NeRF), framing real world objects under one-light-at-time (OLAT) conditions, annotated with accurate ground-truth camera and light poses. Our acquisition pipeline leverages two robotic arms holding, respectively, a camera and an omni-directional point-wise light source. We release a total of 20 scenes depicting a variety of objects with complex geometry and challenging materials. Each scene includes 2000 images, acquired from 50 different points of views under 40 different OLAT conditions. By leveraging the dataset, we perform an ablation study on the relighting capability of variants of the vanilla NeRF architecture and identify a lightweight architecture that can render novel views of an object under novel light conditions, which we use to establish a non-trivial baseline for the dataset. Dataset and benchmark are available at https://eyecan-ai.github.io/rene., Comment: Accepted at CVPR 2023 as a highlight

3D semantic segmentation is a critical task in many real-world applications, such as autonomous driving, robotics, and mixed reality. However, the task is extremely challenging due to ambiguities coming from the unstructured, sparse, and uncolored nature of the 3D point clouds. A possible solution is to combine the 3D information with others coming from sensors featuring a different modality, such as RGB cameras. Recent multi-modal 3D semantic segmentation networks exploit these modalities relying on two branches that process the 2D and 3D information independently, striving to maintain the strength of each modality. In this work, we first explain why this design choice is effective and then show how it can be improved to make the multi-modal semantic segmentation more robust to domain shift. Our surprisingly simple contribution achieves state-of-the-art performances on four popular multi-modal unsupervised domain adaptation benchmarks, as well as better results in a domain generalization scenario., Comment: Accepted at the CVPR2023 Workshop on Autonomous Driving (WAD)

Implicit Neural Representations (INRs) have emerged in the last few years as a powerful tool to encode continuously a variety of different signals like images, videos, audio and 3D shapes. When applied to 3D shapes, INRs allow to overcome the fragmentation and shortcomings of the popular discrete representations used so far. Yet, considering that INRs consist in neural networks, it is not clear whether and how it may be possible to feed them into deep learning pipelines aimed at solving a downstream task. In this paper, we put forward this research problem and propose inr2vec, a framework that can compute a compact latent representation for an input INR in a single inference pass. We verify that inr2vec can embed effectively the 3D shapes represented by the input INRs and show how the produced embeddings can be fed into deep learning pipelines to solve several tasks by processing exclusively INRs., Comment: Accepted at ICLR 2023

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned in a specific setting to solve novel tasks with limited or no additional supervision. In this work, we first show that such knowledge can be shared across tasks by learning a mapping between task-specific deep features in a given domain. Then, we show that this mapping function, implemented by a neural network, is able to generalize to novel unseen domains. Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework. Our proposal obtains compelling results in challenging synthetic-to-real adaptation scenarios by transferring knowledge between monocular depth estimation and semantic segmentation tasks., Comment: Extended version of the paper "Learning Across Tasks and Domains" presented at ICCV 2019. Accepted at TPAMI

Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field., Comment: Extension of the paper "Open Challenges in Deep Stereo: the Booster Dataset" presented at CVPR 2022. Accepted at TPAMI

In this paper, we propose the first-ever real benchmark thought for evaluating Neural Radiance Fields (NeRFs) and, in general, Neural Rendering (NR) frameworks. We design and implement an effective pipeline for scanning real objects in quantity and effortlessly. Our scan station is built with less than 500$ hardware budget and can collect roughly 4000 images of a scanned object in just 5 minutes. Such a platform is used to build ScanNeRF, a dataset characterized by several train/val/test splits aimed at benchmarking the performance of modern NeRF methods under different conditions. Accordingly, we evaluate three cutting-edge NeRF variants on it to highlight their strengths and weaknesses. The dataset is available on our project page, together with an online benchmark to foster the development of better and better NeRFs., Comment: WACV 2023. The first three authors contributed equally. Project page: https://eyecan-ai.github.io/scannerf/

Point cloud classification is a popular task in 3D vision. However, previous works, usually assume that point clouds at test time are obtained with the same procedure or sensor as those at training time. Unsupervised Domain Adaptation (UDA) instead, breaks this assumption and tries to solve the task on an unlabeled target domain, leveraging only on a supervised source domain. For point cloud classification, recent UDA methods try to align features across domains via auxiliary tasks such as point cloud reconstruction, which however do not optimize the discriminative power in the target domain in feature space. In contrast, in this work, we focus on obtaining a discriminative feature space for the target domain enforcing consistency between a point cloud and its augmented version. We then propose a novel iterative self-training methodology that exploits Graph Neural Networks in the UDA context to refine pseudo-labels. We perform extensive experiments and set the new state-of-the-art in standard UDA benchmarks for point cloud classification. Finally, we show how our approach can be extended to more complex tasks such as part segmentation., Comment: WACV 2023, Project Page: https://cvlab-unibo.github.io/FeatureDistillation/

We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural Radiance Fields formulation. X-NeRF optimizes camera poses across spectra during training and exploits Normalized Cross-Device Coordinates (NXDC) to render images of different modalities from arbitrary viewpoints, which are aligned and at the same resolution. Experiments on 16 forward-facing scenes, featuring color, multi-spectral and infrared images, confirm the effectiveness of X-NeRF at modeling Cross-Spectral scene representations., Comment: 3DV 2022. Project page: https://cvlab-unibo.github.io/xnerf-web/

We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences. Purposely, we introduce a novel RGB-MS dataset framing 13 different scenes in indoor environments and providing a total of 34 image pairs annotated with semi-dense, high-resolution ground-truth labels in the form of disparity maps. To tackle the task, we propose a deep learning architecture trained in a self-supervised manner by exploiting a further RGB camera, required only during training data acquisition. In this setup, we can conveniently learn cross-modal matching in the absence of ground-truth labels by distilling knowledge from an easier RGB-RGB matching task based on a collection of about 11K unlabeled image triplets. Experiments show that the proposed pipeline sets a good performance bar (1.16 pixels average registration error) for future research on this novel, challenging task., Comment: CVPR 2022, New Orleans. Project page: https://cvlab-unibo.github.io/rgb-ms-web/

Embedding of large but redundant data, such as images or text, in a hierarchy of lower-dimensional spaces is one of the key features of representation learning approaches, which nowadays provide state-of-the-art solutions to problems once believed hard or impossible to solve. In this work, in a plot twist with a strong meta aftertaste, we show how trained deep models are as redundant as the data they are optimized to process, and how it is therefore possible to use deep learning models to embed deep learning models. In particular, we show that it is possible to use representation learning to learn a fixed-size, low-dimensional embedding space of trained deep models and that such space can be explored by interpolation or optimization to attain ready-to-use models. We find that it is possible to learn an embedding space of multiple instances of the same architecture and of multiple architectures. We address image classification and neural representation of signals, showing how our embedding space can be learnt so as to capture the notions of performance and 3D shape, respectively. In the Multi-Architecture setting we also show how an embedding trained only on a subset of architectures can learn to generate already-trained instances of architectures it never sees instantiated at training time., Comment: Accepted at ICPR2022

We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities. Peculiar to our dataset is the presence of several specular and transparent surfaces, i.e. the main causes of failures for state-of-the-art stereo networks. Our acquisition pipeline leverages a novel deep space-time stereo framework which allows for easy and accurate labeling with sub-pixel precision. We release a total of 419 samples collected in 64 different scenes and annotated with dense ground-truth disparities. Each sample include a high-resolution pair (12 Mpx) as well as an unbalanced pair (Left: 12 Mpx, Right: 1.1 Mpx). Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. We evaluate state-of-the-art deep networks based on our dataset, highlighting their limitations in addressing the open challenges in stereo and drawing hints for future research., Comment: CVPR 2022, New Orleans. Project page: https://cvlab-unibo.github.io/booster-web/

We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that enables to estimate a refined disparity map at any arbitrary output resolution. Thereby, it can handle effectively the unbalanced camera setup typical of nowadays mobile phones, which feature both high and low resolution RGB sensors within the same device. Moreover, our neural network can process seamlessly the output of a variety of stereo methods and, by refining the disparity maps computed by a traditional matching algorithm like SGM, it can achieve unpaired zero-shot generalization performance compared to state-of-the-art end-to-end stereo models., Comment: 3DV 2021 Oral paper. Project page: https://cvlab-unibo.github.io/neural-disparity-refinement-web

Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations. Reliance on multi-task learning to align features across domains has been the standard way to tackle it. In this paper, we take a different path and propose RefRec, the first approach to investigate pseudo-labels and self-training in UDA for point clouds. We present two main innovations to make self-training effective on 3D data: i) refinement of noisy pseudo-labels by matching shape descriptors that are learned by the unsupervised task of shape reconstruction on both domains; ii) a novel self-training protocol that learns domain-specific decision boundaries and reduces the negative impact of mislabelled target samples and in-domain intra-class variability. RefRec sets the new state of the art in both standard benchmarks used to test UDA for point cloud classification, showcasing the effectiveness of self-training for this important problem., Comment: 3DV 2021 (Oral) Code: https://github.com/CVLAB-Unibo/RefRec

Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in the autonomous driving scenario. Previous works usually tackle this issue with Unsupervised Domain Adaptation (UDA), which entails training a network on synthetic images and applying the model to real ones while minimizing the discrepancy between the two domains. Yet, these techniques do not consider additional information that may be obtained from other tasks. Differently, we propose to exploit self-supervised monocular depth estimation to improve UDA for semantic segmentation. On one hand, we deploy depth to realize a plug-in component which can inject complementary geometric cues into any existing UDA method. We further rely on depth to generate a large and varied set of samples to Self-Train the final model. Our whole proposal allows for achieving state-of-the-art performance (58.8 mIoU) in the GTA5->CS benchmark benchmark. Code is available at https://github.com/CVLAB-Unibo/d4-dbst., Comment: Accepted at WACV 2022

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is particularly noticeable along class boundaries, invalidating one of the main goals of semantic segmentation that consists in obtaining sharp segmentation masks. In this work, we specifically address this core problem in the context of Unsupervised Domain Adaptation and present a novel low-level adaptation strategy that allows us to obtain sharp predictions. Moreover, inspired by recent self-training techniques, we introduce an effective data augmentation that alleviates the noise typically present at semantic boundaries when employing pseudo-labels for self-training. Our contributions can be easily integrated into other popular adaptation frameworks, and extensive experiments show that they effectively improve performance along class boundaries., Comment: Accepted at WACV 2022

In this paper we investigate how to effectively deploy deep learning in practical industrial settings, such as robotic grasping applications. When a deep-learning based solution is proposed, usually lacks of any simple method to generate the training data. In the industrial field, where automation is the main goal, not bridging this gap is one of the main reasons why deep learning is not as widespread as it is in the academic world. For this reason, in this work we developed a system composed by a 3-DoF Pose Estimator based on Convolutional Neural Networks (CNNs) and an effective procedure to gather massive amounts of training images in the field with minimal human intervention. By automating the labeling stage, we also obtain very robust systems suitable for production-level usage. An open source implementation of our solution is provided, alongside with the dataset used for the experimental evaluation.

This work introduces a new framework, named SAFFIRE, to automatically extract a dominant recurrent image pattern from a set of image samples. Such a pattern shall be used to eliminate pose variations between samples, which is a common requirement in many computer vision and machine learning tasks. The framework is specialized here in the context of a machine vision system for automated product inspection. Here, it is customary to ask the user for the identification of an anchor pattern, to be used by the automated system to normalize data before further processing. Yet, this is a very sensitive operation which is intrinsically subjective and requires high expertise. Hereto, SAFFIRE provides a unique and disruptive framework for unsupervised identification of an optimal anchor pattern in a way which is fully transparent to the user. SAFFIRE is thoroughly validated on several realistic case studies for a machine vision inspection pipeline., Comment: 14 pages, 23 figures, 2 tables

Defining and reliably finding a canonical orientation for 3D surfaces is key to many Computer Vision and Robotics applications. This task is commonly addressed by handcrafted algorithms exploiting geometric cues deemed as distinctive and robust by the designer. Yet, one might conjecture that humans learn the notion of the inherent orientation of 3D objects from experience and that machines may do so alike. In this work, we show the feasibility of learning a robust canonical orientation for surfaces represented as point clouds. Based on the observation that the quintessential property of a canonical orientation is equivariance to 3D rotations, we propose to employ Spherical CNNs, a recently introduced machinery that can learn equivariant representations defined on the Special Orthogonal group SO(3). Specifically, spherical correlations compute feature maps whose elements define 3D rotations. Our method learns such feature maps from raw data by a self-supervised training procedure and robustly selects a rotation to transform the input point cloud into a learned canonical orientation. Thereby, we realize the first end-to-end learning approach to define and extract the canonical orientation of 3D shapes, which we aptly dub Compass. Experiments on several public datasets prove its effectiveness at orienting local surface patches as well as whole objects., Comment: Accepted to NeurIPS 2020

Depth estimation from stereo images is carried out with unmatched results by convolutional neural networks trained end-to-end to regress dense disparities. Like for most tasks, this is possible if large amounts of labelled samples are available for training, possibly covering the whole data distribution encountered at deployment time. Being such an assumption systematically unmet in real applications, the capacity of adapting to any unseen setting becomes of paramount importance. Purposely, we propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging and ever-changing environments. We design a lightweight and modular architecture, Modularly ADaptive Network (MADNet), and formulate Modular ADaptation algorithms (MAD, MAD++) which permit efficient optimization of independent sub-portions of the entire network. In our paradigm, the learning signals needed to continuously adapt models online can be sourced from self-supervision via right-to-left image warping or from traditional stereo algorithms. With both sources, no other data than the input images being gathered at deployment time are needed. Thus, our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system and pave the way for a new paradigm that can facilitate practical deployment of end-to-end architectures for dense disparity regression., Comment: Extended version of CVPR 2019 paper "Real-time self-adaptive deep stereo" - Accepted to TPAMI

Whole understanding of the surroundings is paramount to autonomous systems. Recent works have shown that deep neural networks can learn geometry (depth) and motion (optical flow) from a monocular video without any explicit supervision from ground truth annotations, particularly hard to source for these two tasks. In this paper, we take an additional step toward holistic scene understanding with monocular cameras by learning depth and motion alongside with semantics, with supervision for the latter provided by a pre-trained network distilling proxy ground truth images. We address the three tasks jointly by a) a novel training protocol based on knowledge distillation and self-supervision and b) a compact network architecture which enables efficient scene understanding on both power hungry GPUs and low-power embedded platforms. We thoroughly assess the performance of our framework and show that it yields state-of-the-art results for monocular depth estimation, optical flow and motion segmentation., Comment: CVPR 2020. Code will be available at https://github.com/CVLAB-Unibo/omeganet

Ambiguity is inherently present in many machine learning tasks, but especially for sequential models seldom accounted for, as most only output a single prediction. In this work we propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data, which is of special importance, as often multiple futures are equally likely. Our approach can be applied to the most common recurrent architectures and can be used with any loss function. Additionally, we introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties and coincides with our intuitive understanding of correctness in the presence of multiple labels. We test our method on several experiments and across diverse tasks dealing with time series data, such as trajectory forecasting and maneuver prediction, achieving promising results.

Object recognition in 3D point clouds is a challenging task, mainly when time is an important factor to deal with, such as in industrial applications. Local descriptors are an amenable choice whenever the 6 DoF pose of recognized objects should also be estimated. However, the pipeline for this kind of descriptors is highly time-consuming. In this work, we propose an update to the traditional pipeline, by adding a preliminary filtering stage referred to as saliency boost. We perform tests on a standard object recognition benchmark by considering four keypoint detectors and four local descriptors, in order to compare time and recognition performance between the traditional pipeline and the boosted one. Results on time show that the boosted pipeline could turn out up to 5 times faster, with the recognition rate improving in most of the cases and exhibiting only a slight decrease in the others. These results suggest that the boosted pipeline can speed-up processing time substantially with limited impacts or even benefits in recognition accuracy., Comment: International Conference on Image Analysis and Processing (ICIAP) 2019

Availability of a few, large-size, annotated datasets, like ImageNet, Pascal VOC and COCO, has lead deep learning to revolutionize computer vision research by achieving astonishing results in several vision tasks.We argue that new tools to facilitate generation of annotated datasets may help spreading data-driven AI throughout applications and domains. In this work we propose Shooting Labels, the first 3D labeling tool for dense 3D semantic segmentation which exploits Virtual Reality to render the labeling task as easy and fun as playing a video-game. Our tool allows for semantically labeling large scale environments very expeditiously, whatever the nature of the 3D data at hand (e.g. point clouds, mesh). Furthermore, Shooting Labels efficiently integrates multiusers annotations to improve the labeling accuracy automatically and compute a label uncertainty map. Besides, within our framework the 3D annotations can be projected into 2D images, thereby speeding up also a notoriously slow and expensive task such as pixel-wise semantic labeling. We demonstrate the accuracy and efficiency of our tool in two different scenarios: an indoor workspace provided by Matterport3D and a large-scale outdoor environment reconstructed from 1000+ KITTI images.

Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors. Recently, a few attempts at applying the deep learning paradigm to the task have shown promising results. Yet, the only explored way to learn rotation invariant descriptors has been to feed neural networks with highly engineered and invariant representations provided by existing hand-crafted descriptors, a path that goes in the opposite direction of end-to-end learning from raw data so successfully deployed for 2D images. In this paper, we explore the benefits of taking a step back in the direction of end-to-end learning of 3D descriptors by disentangling the creation of a robust and distinctive rotation equivariant representation, which can be learned from unoriented input data, and the definition of a good canonical orientation, required only at test time to obtain an invariant descriptor. To this end, we leverage two recent innovations: spherical convolutional neural networks to learn an equivariant descriptor and plane folding decoders to learn without supervision. The effectiveness of the proposed approach is experimentally validated by outperforming hand-crafted and learned descriptors on a standard benchmark., Comment: Accepted to International Conference on Computer Vision 2019

Matching surfaces is a challenging 3D Computer Vision problem typically addressed by local features. Although a variety of 3D feature detectors and descriptors has been proposed in literature, they have seldom been proposed together and it is yet not clear how to identify the most effective detector-descriptor pair for a specific application. A promising solution is to leverage machine learning to learn the optimal 3D detector for any given 3D descriptor [15]. In this paper, we report a performance evaluation of the detector-descriptor pairs obtained by learning a paired 3D detector for the most popular 3D descriptors. In particular, we address experimental settings dealing with object recognition and surface registration.

State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in appearance and/or context from those observed at training time. This domain shift issue is usually addressed by fine-tuning on smaller sets of images from the target domain annotated with depth labels. Unfortunately, relying on such supervised labeling is seldom feasible in most practical settings. Therefore, we propose an unsupervised domain adaptation technique which does not require groundtruth labels. Our method relies only on image pairs and leverages on classical stereo algorithms to produce disparity measurements alongside with confidence estimators to assess upon their reliability. We propose to fine-tune both depth-from-stereo as well as depth-from-mono architectures by a novel confidence-guided loss function that handles the measured disparities as noisy labels weighted according to the estimated confidence. Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation., Comment: 14 pages, 7 pages. Accepted to TPAMI

In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera tracking, and an augmented reality pen to define initial object bounding box, to create large labeled datasets with minimal human intervention. By removing the burden of generating annotated data from humans, we make the Deep Learning technique applied to computer vision, that typically requires very large datasets, truly automated and reliable. With the ARS pipeline, we created effortlessly two novel datasets, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario), and trained robustly two state-of-the-art object detectors, based on convolutional neural networks, such as YOLO and SSD. With respect to the conventional manual annotation of 1000 frames that takes us slightly more than 10 hours, the proposed approach based on ARS allows annotating 9 sequences of about 35000 frames in less than one hour, with a gain factor of about 450. Moreover, both the precision and recall of object detection is increased by about 15\% with respect to manual labeling. All our software is available as a ROS package in a public repository alongside the novel annotated datasets.

Obtaining highly accurate depth from stereo images in real time has many applications across computer vision and robotics, but in some contexts, upper bounds on power consumption constrain the feasible hardware to embedded platforms such as FPGAs. Whilst various stereo algorithms have been deployed on these platforms, usually cut down to better match the embedded architecture, certain key parts of the more advanced algorithms, e.g. those that rely on unpredictable access to memory or are highly iterative in nature, are difficult to deploy efficiently on FPGAs, and thus the depth quality that can be achieved is limited. In this paper, we leverage a FPGA-CPU chip to propose a novel, sophisticated, stereo approach that combines the best features of SGM and ELAS-based methods to compute highly accurate dense depth in real time. Our approach achieves an 8.7% error rate on the challenging KITTI 2015 dataset at over 50 FPS, with a power consumption of only 5W., Comment: 6 pages, 7 figures, 2 tables, journal

Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical methodologies to transfer learned concepts across different training processes. In this work, we introduce a novel adaptation framework that can operate across both task and domains. Our framework learns to transfer knowledge across tasks in a fully supervised domain (e.g., synthetic data) and use this knowledge on a different domain where we have only partial supervision (e.g., real data). Our proposal is complementary to existing domain adaptation techniques and extends them to cross tasks scenarios providing additional performance gains. We prove the effectiveness of our framework across two challenging tasks (i.e., monocular depth estimation and semantic segmentation) and four different domains (Synthia, Carla, Kitti, and Cityscapes)., Comment: Accepted at ICCV 2019

Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in the environment, making them less suitable for practical applications such as autonomous driving. In this work, we introduce a "learning-to-adapt" framework that enables deep stereo methods to continuously adapt to new target domains in an unsupervised manner. Specifically, our approach incorporates the adaptation procedure into the learning objective to obtain a base set of parameters that are better suited for unsupervised online adaptation. To further improve the quality of the adaptation, we learn a confidence measure that effectively masks the errors introduced during the unsupervised adaptation. We evaluate our method on synthetic and real-world stereo datasets and our experiments evidence that learning-to-adapt is, indeed beneficial for online adaptation on vastly different domains., Comment: Accepted at CVPR2019. Code available at https://github.com/CVLAB-Unibo/Learning2AdaptForStereo

Recognizing packaged grocery products based solely on appearance is still an open issue for modern computer vision systems due to peculiar challenges. Firstly, the number of different items to be recognized is huge (i.e., in the order of thousands) and rapidly changing over time. Moreover, there exist a significant domain shift between the images that should be recognized at test time, taken in stores by cheap cameras, and those available for training, usually just one or a few studio-quality images per product. We propose an end-to-end architecture comprising a GAN to address the domain shift at training time and a deep CNN trained on the samples generated by the GAN to learn an embedding of product images that enforces a hierarchy between product categories. At test time, we perform recognition by means of K-NN search against a database consisting of just one reference image per product. Experiments addressing recognition of products present in the training datasets as well as different ones unseen at training time show that our approach compares favourably to state-of-the-art methods on the grocery recognition task and generalize fairly well to similar ones.

Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, or establish correspondences between keypoints in the image and points in the scene to estimate the pose. In recent years, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but have traditionally needed to be trained offline on the target scene, preventing relocalisation in new environments. Recently, we showed how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. The adapted forests achieved relocalisation performance that was on par with that of offline forests, and our approach was able to estimate the camera pose in close to real time. In this paper, we present an extension of this work that achieves significantly better relocalisation performance whilst running fully in real time. To achieve this, we make several changes to the original approach: (i) instead of accepting the camera pose hypothesis without question, we make it possible to score the final few hypotheses using a geometric approach and select the most promising; (ii) we chain several instantiations of our relocaliser together in a cascade, allowing us to try faster but less accurate relocalisation first, only falling back to slower, more accurate relocalisation as necessary; and (iii) we tune the parameters of our cascade to achieve effective overall performance. These changes allow us to significantly improve upon the performance our original state-of-the-art method was able to achieve on the well-known 7-Scenes and Stanford 4 Scenes benchmarks. As additional contributions, we present a way of visualising the internal behaviour of our forests and show how to entirely circumvent the need to pre-train a forest on a generic scene., Comment: Tommaso Cavallari, Stuart Golodetz, Nicholas Lord and Julien Valentin assert joint first authorship

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like semantic segmentation. Recent works have proposed to rely on synthetically generated imagery to ease the training set creation. However, models trained on these kind of data usually under-perform on real images due to the well known issue of domain shift. We address this problem by learning a domain-to-domain image translation GAN to shrink the gap between real and synthetic images. Peculiarly to our method, we introduce semantic constraints into the generation process to both avoid artifacts and guide the synthesis. To prove the effectiveness of our proposal, we show how a semantic segmentation CNN trained on images from the synthetic GTA dataset adapted by our method can improve performance by more than 16% mIoU with respect to the same model trained on synthetic images., Comment: 6 pages, Accepted to IPAS 2018

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs. These models, however, suffer from a notable decrease in accuracy when exposed to scenarios significantly different from the training set, e.g., real vs synthetic images, etc.). We argue that it is extremely unlikely to gather enough samples to achieve effective training/tuning in any target domain, thus making this setup impractical for many applications. Instead, we propose to perform unsupervised and continuous online adaptation of a deep stereo network, which allows for preserving its accuracy in any environment. However, this strategy is extremely computationally demanding and thus prevents real-time inference. We address this issue introducing a new lightweight, yet effective, deep stereo architecture, Modularly ADaptive Network (MADNet) and developing a Modular ADaptation (MAD) algorithm, which independently trains sub-portions of the network. By deploying MADNet together with MAD we introduce the first real-time self-adaptive deep stereo system enabling competitive performance on heterogeneous datasets., Comment: Accepted at CVPR2019 as oral presentation. Code Available https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo

While robotic manipulation of rigid objects is quite straightforward, coping with deformable objects is an open issue. More specifically, tasks like tying a knot, wiring a connector or even surgical suturing deal with the domain of Deformable Linear Objects (DLOs). In particular the detection of a DLO is a non-trivial problem especially under clutter and occlusions (as well as self-occlusions). The pose estimation of a DLO results into the identification of its parameters related to a designed model, e.g. a basis spline. It follows that the stand-alone segmentation of a DLO might not be sufficient to conduct a full manipulation task. This is why we propose a novel framework able to perform both a semantic segmentation and b-spline modeling of multiple deformable linear objects simultaneously without strict requirements about environment (i.e. the background). The core algorithm is based on biased random walks over the Region Adiacency Graph built on a superpixel oversegmentation of the source image. The algorithm is initialized by a Convolutional Neural Networks that detects the DLO's endcaps. An open source implementation of the proposed approach is also provided to easy the reproduction of the whole detection pipeline along with a novel cables dataset in order to encourage further experiments., Comment: Accepted as Oral to ACCV 2018, Perth

Depth estimation from a single image represents a very exciting challenge in computer vision. While other image-based depth sensing techniques leverage on the geometry between different viewpoints (e.g., stereo or structure from motion), the lack of these cues within a single image renders ill-posed the monocular depth estimation task. For inference, state-of-the-art encoder-decoder architectures for monocular depth estimation rely on effective feature representations learned at training time. For unsupervised training of these models, geometry has been effectively exploited by suitable images warping losses computed from views acquired by a stereo rig or a moving camera. In this paper, we make a further step forward showing that learning semantic information from images enables to improve effectively monocular depth estimation as well. In particular, by leveraging on semantically labeled images together with unsupervised signals gained by geometry through an image warping loss, we propose a deep learning approach aimed at joint semantic segmentation and depth estimation. Our overall learning framework is semi-supervised, as we deploy groundtruth data only in the semantic domain. At training time, our network learns a common feature representation for both tasks and a novel cross-task loss function is proposed. The experimental findings show how, jointly tackling depth prediction and semantic segmentation, allows to improve depth estimation accuracy. In particular, on the KITTI dataset our network outperforms state-of-the-art methods for monocular depth estimation., Comment: 16 pages, Accepted to ACCV 2018

Recognition of grocery products in store shelves poses peculiar challenges. Firstly, the task mandates the recognition of an extremely high number of different items, in the order of several thousands for medium-small shops, with many of them featuring small inter and intra class variability. Then, available product databases usually include just one or a few studio-quality images per product (referred to herein as reference images), whilst at test time recognition is performed on pictures displaying a portion of a shelf containing several products and taken in the store by cheap cameras (referred to as query images). Moreover, as the items on sale in a store as well as their appearance change frequently over time, a practical recognition system should handle seamlessly new products/packages. Inspired by recent advances in object detection and image retrieval, we propose to leverage on state of the art object detectors based on deep learning to obtain an initial productagnostic item detection. Then, we pursue product recognition through a similarity search between global descriptors computed on reference and cropped query images. To maximize performance, we learn an ad-hoc global descriptor by a CNN trained on reference images based on an image embedding loss. Our system is computationally expensive at training time but can perform recognition rapidly and accurately at test time.

The arrangement of products in store shelves is carefully planned to maximize sales and keep customers happy. However, verifying compliance of real shelves to the ideal layout is a costly task routinely performed by the store personnel. In this paper, we propose a computer vision pipeline to recognize products on shelves and verify compliance to the planned layout. We deploy local invariant features together with a novel formulation of the product recognition problem as a sub-graph isomorphism between the items appearing in the given image and the ideal layout. This allows for auto-localizing the given image within the aisle or store and improving recognition dramatically., Comment: Slightly extended version of the paper accepted at ICIAP 2017. More information @project_page --> http://vision.disi.unibo.it/index.php?option=com_content&view=article&id=111&catid=78

We present a novel mapping framework for robot navigation which features a multi-level querying system capable to obtain rapidly representations as diverse as a 3D voxel grid, a 2.5D height map and a 2D occupancy grid. These are inherently embedded into a memory and time efficient core data structure organized as a Tree of SkipLists. Compared to the well-known Octree representation, our approach exhibits a better time efficiency, thanks to its simple and highly parallelizable computational structure, and a similar memory footprint when mapping large workspaces. Peculiarly within the realm of mapping for robot navigation, our framework supports realtime erosion and re-integration of measurements upon reception of optimized poses from the sensor tracker, so as to improve continuously the accuracy of the map., Comment: Accepted by International Conference on Robotics and Automation (ICRA) 2017. This is the submitted version. The final published version may be slightly different

Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for real-time systems that require online relocalisation., Comment: To appear in the proceedings of CVPR 2017