activity
20232026
collaborators

5 papers

cs.CV2026

A Persistent Homology Design Space for 3D Point Cloud Deep Learning

Prachi Kudeshia, Jiju Poovvancheri, Amr Ghoneim +1

Persistent Homology (PH) offers stable, multi-scale descriptors of intrinsic shape structure by capturing connected components, loops, and voids that persist across scales, providi…

cs.CV2026

Learning Significant Persistent Homology Features for 3D Shape Understanding

Prachi Kudeshia, Jiju Poovvancheri

Geometry and topology constitute complementary descriptors of three-dimensional shape, yet existing benchmark datasets primarily capture geometric information while neglecting topo…

cs.CV2024

DepGAN: Leveraging Depth Maps for Handling Occlusions and Transparency in Image Composition

Amr Ghoneim, Jiju Poovvancheri, Yasushi Akiyama +1

Image composition is a complex task which requires a lot of information about the scene for an accurate and realistic composition, such as perspective, lighting, shadows, occlusion…

cs.CV2024

Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud

Ayumu Saito, Prachi Kudeshia, Jiju Poovvancheri

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including len…

cs.CV2023

RBF Weighted Hyper-Involution for RGB-D Object Detection

Mehfuz A Rahman, Khushal Das, Jiju Poovvancheri +2

A vast majority of augmented reality devices come equipped with depth and color cameras. Despite their advantages, extracting both photometric and depth features simultaneously in…