Measurement-aware models
The measurement shapes the model.
Spectral absorption, species identification, brain anatomy, crystallographic symmetry, and 3D cell structure each shape the method.
Center for Multimodal Learning
UCSB Electrical and Computer Engineering
We build computer vision systems around the measurements that make science difficult: label-free 3D microscopy, hyperspectral remote sensing, aerial ecology, clinical neuroimaging, materials characterization, and the image infrastructure that turns those methods into reproducible research.
Bright 4B Computer vision Multimodal learning Scientific image informatics Reproducible AI systems
Shared substrate
BisQue keeps data, metadata, annotation, and visualization close.
The platform gives research code a browser-visible path into datasets, modules, and inspectable outputs.
Research infrastructure
BisQue Ultra turns methods into inspectable scientific work.
Ultra connects complex scientific files, viewers, tools, durable runs, model training, and reproducible artifacts in one workbench.
Bright 4B
Bright 4B scales hyperspherical learning to 3D brightfield microscopy.
Bright 4B is a 4B-parameter foundation model that learns on the unit hypersphere to segment subcellular structures directly from 3D brightfield volumes. Native Sparse Attention, residual HyperConnections, soft Mixture-of-Experts, and anisotropic patch embedding address context, representation flow, adaptive capacity, and confocal geometry without requiring fluorescence or handcrafted post-processing.
Representation
PSF-aware patch embeddings preserve axial structure.
The model respects point-spread behavior and axial thinning before global reasoning begins, preserving fine structure across depth.
Biological output
Label-free masks become inspectable scientific evidence.
Nuclei, mitochondria, microtubules, and related structures can be compared as segmentation outputs rather than treated as opaque model responses.
Research programs
Published computer vision across five scientific domains.
The lab's public work spans remote sensing, ecology, clinical neuroimaging, materials science, and bioimage analysis. Each program begins with the geometry, physics, or biology of the measurement and ends with code, data, or a platform path that other researchers can inspect.
01
Hyperspectral remote sensing
Spectral-absorption-aware transformers for methane detection
Detects methane plumes from airborne hyperspectral imagery with a model designed around absorption wavelengths, plus the public Methane HotSpot dataset and BisQue visualization tooling.
CVPR 2023 Highlight
The repository includes source code, pretrained plume detection and segmentation weights, MHS dataset download scripts, and a BisQue online dataset viewer.
02
Ecological computer vision
Aerial image analysis for multi-species detection and identification
Turns aerial imagery into detection, localization, and species-identification signals for wildlife monitoring, grounded in a verified dataset of 11k images and 28k annotations.
CVPR 2024
The public repository ships model code, pretrained detector weights, dataset tooling, and a BisQue visualization route for the Mara-Wildlife dataset.
03
Materials microscopy
Physics-based super-resolution for electron backscatter diffraction maps
Adapts super-resolution to EBSD orientation maps using crystallographic symmetry, quaternion-aware orientation recognition, and physics-aware losses.
npj Computational Materials 2022
The project connects network training, inference, IPF-map visualization, and BisQue module deployment for high-throughput materials characterization.
04
Clinical neuroimaging
Location-aware patch-based CNNs for MRI brain tumor segmentation
Improves glioma segmentation by registering a brain parcellation atlas into each subject space and combining that location signal with multimodal MR images, 3D U-Net, DeepMedic, and ensemble learning.
Frontiers in Neuroscience 2020
The paper reports that location information improves patch-based neural networks for BraTS brain tumor segmentation and uses model diversity plus uncertainty reduction in a two-level ensemble.
05
Clinical neuroimage analysis
Automated CT segmentation and connectome-aware NPH prediction
Segments regions of interest from CT brain scans, combines them with diffusion tractography and connectome features, and predicts Normal Pressure Hydrocephalus from measurable neuroanatomy.
BME Frontiers 2022
The article describes an automated NPH prediction method from CT scans that incorporates MRI diffusion tractography information, with reported gains over prior state-of-the-art precision and recall.
06
Bioimage analysis
Segmentation, tracking, and sub-cellular feature extraction in 3D time-lapse images
Turns time-lapse 3D confocal image stacks into quantitative cell histories with rotation-equivariant 3D segmentation, adjacency-graph feature extraction, and graph-based tracking.
Scientific Reports 2023
The Scientific Reports paper states that code is available on GitHub and the method is available as a service through the BisQue portal.
Platform layer
Research methods become more useful when the infrastructure is shared.
BisQue, Bright 4B, BisQue Ultra, and the public research repositories form one visible chain: scientific data enters a scalable image platform, domain-shaped models operate close to the data, and the workbench preserves the run, outputs, and evidence.
01 BisQue image informatics Store, annotate, search, visualize, and run scientific image analyses. 02 Scientific vision methods Publish domain-shaped models, datasets, weights, and reproducible code paths. 03 BisQue Ultra workbench Connect data, model-guided work, training decisions, and durable artifacts.
Collaborate
Work with us on the next scientific vision system.
We collaborate with researchers and infrastructure teams on new imaging methods, multimodal datasets, model evaluation, scientific viewers, and reproducible AI workflows.
Publications and code