Search Results for author:
Found 17 papers, 11 papers with code
Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data
This unsupervised approach allows the generated data to capture the vast complexity of the real world while maintaining the precision and scale of synthetic data.
One-shot recognition of any material anywhere using contrastive learning with physics-based rendering
The synthetic images were rendered using giant collections of textures, objects, and environments generated by computer graphics artists.
Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
For that, we use more than 100, 000 research papers and build up a knowledge network with more than 64, 000 concept nodes.
Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects
To address the shortcomings of existing transparent object data collection schemes in literature, we also propose an automated dataset creation workflow that consists of robot-controlled image collection and vision-based automatic annotation.
Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI dataset
We use this to predict 3D models of vessels and their content from a single image.
Ranked #1 on
Single-View 3D Reconstruction
on TransProteus
Computer vision for liquid samples in hospitals and medical labs using hierarchical image segmentation and relations prediction
This work explores the use of computer vision for image segmentation and classification of medical fluid samples in transparent containers (for example, tubes, syringes, infusion bags).
Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations
We expect that extending PASITHEA to larger datasets, molecules and more complex properties will lead to advances in the design of new functional molecules as well as the interpretation and explanation of machine learning models.
Computer Vision for Recognition of Materials and Vessels in Chemistry Lab Settings and the Vector-LabPics Data Set
Visual recognition of vessels and their contents is essential for performing this task.
Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into parts
The generator/evaluator approach for this case consists of two independent convolutional neural nets: a generator net that suggests variety segments corresponding to objects, stuff and parts regions in the image, and an evaluator net that chooses the best segments to be merged into the segmentation map.
Ranked #37 on
Panoptic Segmentation
on COCO test-dev
Class-independent sequential full image segmentation, using a convolutional net that finds a segment within an attention region, given a pointer pixel within this segment
The net was tested and trained on the COCO panoptic dataset and achieved 67% IOU for segmentation of familiar classes (that were part of the net training set) and 53% IOU for segmentation of unfamiliar classes (that were not included in the training).
Classifying a specific image region using convolutional nets with an ROI mask as input
This goal is achieved using a standard image classification net with the addition of a side branch, which converts the ROI mask into an attention map.
Hierarchical semantic segmentation using modular convolutional neural networks
It applies one fully convolutional neural net to segment the image into vessel and background, and the vessel region is used as an input for a second net which recognizes the contents of the glass vessel.
Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels
This valve filter effectively acts as a valve that inhibits specific features in different image regions according to the ROI map.
Tracing liquid level and material boundaries in transparent vessels using the graph cut computer vision approach
The bottom 10% of the vessel region in the image is assumed to correspond to the material phase and defined as the graph and source.
Using curvature to distinguish between surface reflections and vessel contents in computer vision based recognition of materials in transparent vessels
Reflections and the functional parts of a vessels surface can create strong edges that can be mistakenly identified as corresponding to the vessel contents, and cause recognition errors.
Tracing the boundaries of materials in transparent vessels using computer vision
The probability that a curve matches the material boundary in the image is evaluated using a cost function based on some image properties along this curve.
Computer vision-based recognition of liquid surfaces and phase boundaries in transparent vessels, with emphasis on chemistry applications
The method then compares each curve to the image to rate its correspondence with the outline of the real liquid surface by examining various image properties in the area surrounding each point of the curve.
