Salma Galaaoui

Papers

Total Citations

H-Index

About

Salma Galaaoui is a rising researcher in computer vision, with a focus on 3D reconstruction and hand-object interaction modeling. Her work addresses a critical gap in the field: the limited variability of real objects in existing hand-object datasets and the over-reliance on parametric models like MANO for groundtruth hand shapes. To overcome these limitations, she introduced the **SHOWMe dataset**, a benchmark comprising 96 videos annotated with real, diverse objects—enabling more robust, object-agnostic 3D reconstruction from RGB video. Her two most-cited papers, published in 2023 and 2024, have already garnered 9 and 8 citations respectively, signaling strong early impact in a competitive domain. By pushing beyond synthetic or constrained setups, Galaaoui’s contributions are foundational for applications in augmented reality, robotics, and human-computer interaction, where accurate, real-world hand-object reconstruction is essential. Her work exemplifies how careful dataset design can drive algorithmic progress, and she is quickly establishing herself as a key voice in the next generation of 3D vision researchers.