
3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing...
Feb 1, 2023 · In this work, we propose a lightweight volumetric ConvNet, termed 3D UX-Net, which adapts the hierarchical transformer using ConvNet modules for robust volumetric segmentation.
MedGMAE: Gaussian Masked Autoencoders for Medical Volumetric ...
Sep 15, 2025 · TL;DR: MedGMAE replaces traditional voxel-level reconstruction in medical volumetric data pre-training with 3D Gaussian primitives prediction, enabling more effective anatomical …
Learning General-purpose Biomedical Volume Representations using ...
Jan 22, 2025 · This work proposes a pre-training approach for downstream tasks related to fine-grained volumetric medical data: image registration and semantic segmentation. The authors propose to …
6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric ...
Jan 22, 2025 · Keywords: 3D Gaussian splatting, 6D Gaussian splatting, volumetric rendering TL;DR: The paper introduces 6D Gaussian Splatting (6DGS) for real-time radiance field rendering. It …
ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical...
May 11, 2021 · Inspired by them, we present ViT-V-Net, which bridges ViT and ConvNet to provide volumetric medical image registration. The experimental results presented here demonstrate that the …
Inspired by them, we present ViT-V-Net, which bridges ViT and ConvNet to provide volumetric medical image registration. The experimental results presented here demonstrate that the proposed …
What can Mamba do for 3D Volumetric Medical Image Segmentation?
Sep 24, 2024 · What can Mamba do for 3D Volumetric Medical Image Segmentation? Chaohan Wang, Qi Chen, Yuyin Zhou, Qi Wu, Yutong Xie
In this work, we propose a lightweight volumetric ConvNet, termed 3D UX-Net, which adapts the hierar- chical transformer using ConvNet modules for robust volumetric segmentation.
finetuning scenarios with volumetric multi-organ/tissues segmentation. 3D UX-Net achieves consistently improvement in both scenarios across all ConvNets and transform-ers SOTA with fewer model …
SegVol: Universal and Interactive Volumetric Medical Image...
Sep 25, 2024 · This model supports universal and interactive volumetric medical image segmentation of more than 200 anatomical categories. This model is also well-designed with spatial and semantic …