Search Results for author:
Found 53 papers, 22 papers with code
Connecting NeRFs, Images, and Text
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.
Test Time Training for Industrial Anomaly Segmentation
Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control.
Deep Learning on 3D Neural Fields
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.
Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies.
Neural Processing of Tri-Plane Hybrid Neural 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.
Looking at words and points with attention: a benchmark for text-to-shape coherence
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.
Learning Depth Estimation for Transparent and Mirror Surfaces
Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks.
ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects
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.
Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation
3D semantic segmentation is a critical task in many real-world applications, such as autonomous driving, robotics, and mixed reality.
Deep Learning on Implicit Neural Representations of Shapes
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.
Learning Good Features to Transfer Across Tasks and 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.
Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces
Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization.
ScanNeRF: a Scalable Benchmark for Neural Radiance Fields
In this paper, we propose the first-ever real benchmark thought for evaluating Neural Radiance Fields (NeRFs) and, in general, Neural Rendering (NR) frameworks.
Self-Distillation for Unsupervised 3D Domain Adaptation
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.
Cross-Spectral Neural Radiance Fields
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.
RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation
We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences.
Learning the Space of Deep 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.
Open Challenges in Deep Stereo: the Booster Dataset
We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities.
Neural Disparity Refinement for Arbitrary Resolution Stereo
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.
RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation
Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations.
Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation
We further rely on depth to generate a large and varied set of samples to Self-Train the final model.
Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries
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.
Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings
In this paper we investigate how to effectively deploy deep learning in practical industrial settings, such as robotic grasping applications.
SAFFIRE: System for Autonomous Feature Filtering and Intelligent ROI Estimation
The framework is specialized here in the context of a machine vision system for automated product inspection.
Learning to Orient Surfaces by Self-supervised Spherical CNNs
In this work, we show the feasibility of learning a robust canonical orientation for surfaces represented as point clouds.
Continual Adaptation for Deep Stereo
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.
Distilled Semantics for Comprehensive Scene Understanding from Videos
Whole understanding of the surroundings is paramount to autonomous systems.
Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models
Ambiguity is inherently present in many machine learning tasks, but especially for sequential models seldom accounted for, as most only output a single prediction.
Boosting Object Recognition in Point Clouds by Saliency Detection
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.
Shooting Labels: 3D Semantic Labeling by Virtual Reality
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.
Learning an Effective Equivariant 3D Descriptor Without Supervision
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors.
Performance Evaluation of Learned 3D Features
Matching surfaces is a challenging 3D Computer Vision problem typically addressed by local features.
Unsupervised Domain Adaptation for Depth Prediction from Images
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.
Semi-Automatic Labeling for Deep Learning in Robotics
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.
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
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.
Learning Across Tasks and Domains
Recent works have proven that many relevant visual tasks are closely related one to another.
Learning to Adapt for Stereo
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment.
Domain invariant hierarchical embedding for grocery products recognition
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.
Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade
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.
Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
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.
Real-time self-adaptive deep stereo
Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs.
Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation
While robotic manipulation of rigid objects is quite straightforward, coping with deformable objects is an open issue.
Geometry meets semantics for semi-supervised monocular depth estimation
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.
A deep learning pipeline for product recognition on store shelves
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).
Unsupervised Adaptation for Deep Stereo
Recent ground-breaking works have shown that deep neural networks can be trained end-to-end to regress dense disparity maps directly from image pairs.
Product recognition in store shelves as a sub-graph isomorphism problem
The arrangement of products in store shelves is carefully planned to maximize sales and keep customers happy.
SkiMap: An Efficient Mapping Framework for Robot Navigation
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.
On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation
Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation.
Learning a Descriptor-Specific 3D Keypoint Detector
Keypoint detection represents the first stage in the majority of modern computer vision pipelines based on automatically established correspondences between local descriptors.
Volume-based Semantic Labeling with Signed Distance Functions
Research works on the two topics of Semantic Segmentation and SLAM (Simultaneous Localization and Mapping) have been following separate tracks.
Large-Scale and Drift-Free Surface Reconstruction Using Online Subvolume Registration
Our method supports online model correction, without needing to reprocess or store any input depth data.
Keypoints from Symmetries by Wave Propagation
The paper conjectures and demonstrates that repeatable keypoints based on salient symmetries at different scales can be detected by a novel analysis grounded on the wave equation rather than the heat equation underlying traditional Gaussian scale-space theory.
Joint Detection, Tracking and Mapping by Semantic Bundle Adjustment
In this paper we propose a novel Semantic Bundle Adjustment framework whereby known rigid stationary objects are detected while tracking the camera and mapping the environment.
