47 citations · 94 across the 8 of their papers we have counts for
10 papers
Towards Fast and Scalable Normal Integration using Continuous Components
Francesco Milano, Jen Jen Chung, Lionel Ott +1
Surface normal integration is a fundamental problem in computer vision, dealing with the objective of reconstructing a surface from its corresponding normal map. Existing approache…
Discontinuity-aware Normal Integration for Generic Central Camera Models
Francesco Milano, Manuel López-Antequera, Naina Dhingra +2
Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-sh…
NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models
Francesco Milano, Jen Jen Chung, Hermann Blum +2
State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines f…
ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification
Nicolas Gorlo, Kenneth Blomqvist, Francesco Milano +1
Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class…
Panoptic Vision-Language Feature Fields
Haoran Chen, Kenneth Blomqvist, Francesco Milano +1
Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provide…
Neural Implicit Vision-Language Feature Fields
Kenneth Blomqvist, Francesco Milano, Jen Jen Chung +2
Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided…
Unsupervised Continual Semantic Adaptation through Neural Rendering
Zhizheng Liu, Francesco Milano, Jonas Frey +3
An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deploym…
Continual Adaptation of Semantic Segmentation using Complementary 2D-3D Data Representations
Jonas Frey, Hermann Blum, Francesco Milano +2
Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the traini…
Self-Improving Semantic Perception for Indoor Localisation
Hermann Blum, Francesco Milano, René Zurbrügg +3
We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fi…
Primal-Dual Mesh Convolutional Neural Networks
Francesco Milano, Antonio Loquercio, Antoni Rosinol +2
Recent works in geometric deep learning have introduced neural networks that allow performing inference tasks on three-dimensional geometric data by defining convolution, and somet…