Mert Kiray
YOU?
Author Swipe
View article: Dropping the D: RGB-D SLAM Without the Depth Sensor
Dropping the D: RGB-D SLAM Without the Depth Sensor Open
We present DropD-SLAM, a real-time monocular SLAM system that achieves RGB-D-level accuracy without relying on depth sensors. The system replaces active depth input with three pretrained vision modules: a monocular metric depth estimator, …
View article: MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition
MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition Open
Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton convention, which limits th…
View article: PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation Open
Visual effects (VFX) are key to immersion in modern films, games, and AR/VR. Creating 3D effects requires specialized expertise and training in 3D animation software and can be time consuming. Generative solutions typically rely on computa…