Hosted on MSN

Upsampling method sharpens AI vision with up to 16 times less GPU memory

From facial recognition on smartphones to humanoid robots, computer vision technology, which serves as the eyes of artificial intelligence (AI), is widely used in daily life. A joint research team ...
IEEE

PU-Flow: A Point Cloud Upsampling Network With Normalizing Flows

Abstract: Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, ...
IEEE

SUP-Net: Slow-time Upsampling Network for Aliasing Removal in Doppler Ultrasound

Abstract: Doppler ultrasound modalities, which include spectral Doppler and color flow imaging, are frequently used tools for flow diagnostics because of their real-time point-of-care applicability ...
GitHub

PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks (CVPR21')

2026/06/02: add fixes and troubleshooting notes for open GitHub issues: safe FPS indexing during test, corrected Hausdorff calculation, more robust CGAL evaluation compilation/P2F handling, HDF5 ...
GitHub

ViT-Up: Faithful Feature Upsampling for Vision Transformers

ViT-Up is an implicit feature upsampler for Vision Transformers that predicts backbone-aligned features at arbitrary continuous image coordinates. Pretrained through self-supervised feature ...