Resolving hand‐object occlusion for mixed reality with joint deep learning and model optimization

Abstract

By overlaying virtual imagery onto the real world, mixed reality facilitates diverse applications and has drawn increasing attention. Enhancing physical in-hand objects with a virtual appearance is a key component for many applications that require users to interact with tools such as surgery simulations. However, due to complex hand articulations and severe hand-object occlusions, resolving occlusions in hand-object interactions is a challenging topic. Traditional tracking-based approaches are limited by strong ambiguities from occlusions and changing shapes, while reconstruction-based methods show a poor capability of handling dynamic scenes. In this article, we propose a novel real-time optimization system to resolve hand-object occlusions by spatially reconstructing the scene with estimated hand joints and masks. To acquire accurate results, we propose a joint learning process that shares information between two models and jointly estimates hand poses and semantic segmentation. To facilitate the joint learning system and improve its accuracy under occlusions, we propose an occlusion-aware RGB-D hand data set that mitigates the ambiguity through precise annotations and photorealistic appearance. Evaluations show more consistent overlays compared with literature, and a user study verifies a more realistic experience.

Emerging Challenges in Technology-based Support for Surgical Training

“…To generate critical situations (e.g., simulated bleeding) effectively given an MR rendering interface, algorithms for real-time interactions between real and virtual objects [20] are needed. For instance, a depth map generation algorithm is utilized to handle occlusion interactions [21]. Object recognition and tracking schemes [22] are also required for the MR rendering.…”

A Mixed Reality Training System for Hand-Object Interaction in Simulated Microgravity Environments

“…Hand-object interaction is a fundamental aspect of MR experiences, as it enables users to engage with and manipulate virtual objects in a more intuitive and immersive manner [19]. We will provide an overview of the advancements made in enhancing hand-object interaction in MR from two perspectives: hand perception techniques and interaction relationship reasoning.…”