GitHub

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on ...
IEEE

PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models

Abstract: We introduce PerfCam, an open source Proof-of-Concept (PoC) digital twinning framework that combines camera and sensory data with 3D Gaussian Splatting and computer vision models for digital ...
IEEE

Adaptability of Vision Foundation Models for 3D Medical Image Segmentation

Abstract: Vision Foundation Models (VFMs), such as DINOv2 and SAM, have demonstrated unprecedented generalizability in natural imaging and show strong promise in medical imaging due to their ...
GitHub

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction (CVPR 2026)

VLM-3R is a unified Vision-Language Model (VLM) framework integrating 3D reconstructive instruction tuning for deep spatial understanding from monocular video. The rapid advancement of Large ...