🎉 Latest News: Our paper on "Vision-Language Transformers in 3D MRI Synthesis" has been accepted at MICCAI 2026!
Home > Projects > OmniVision-3D: Self-Supervised Vision Tr...
OmniVision-3D: Self-Supervised Vision Transformers for Volumetric Scans
3D Computer Vision Ongoing
Grant Funded ($1.2M)

OmniVision-3D: Self-Supervised Vision Transformers for Volumetric Scans

Lead Investigator: Dr. Sarah Chen

Executive Summary

Pre-training 3D transformers on 150,000 unannotated volumetric scans for zero-shot tumor detection and organ segmentation.

Technology Stack & Domain Frameworks

Self-Supervised 3D CT/MRI Transformers

Methodology & Clinical Validation

Project Overview: OmniVision-3D introduces masked autoencoder pre-training natively designed for 3D spatial grids, dramatically reducing the need for dense voxel manual annotations.

Related Research Projects