Youngbin Kim

A WISE (Wearable Interface for Sustainable Enhancement) AR UI/UX platform for smart glasses.

We present a spatial augmentation system designed for Augmented Reality (AR) exhibition experiences, focusing on the immersive reinterpretation of two-dimensional artworks. Existing AR exhibition applications primarily augment content related to the artwork, but fall short of its architectural elements, which are crucial for integrating the artwork into the viewer’s surrounding space and enabling immersive spatial alignment. This study proposes a spatial augmentation approach that takes an artwork image as input, generates floor patterns and architectural 3D models through 2D and 3D model generation pipelines, and semantically aligns and augments them in the physical space. This spatial augmentation intends to enhance viewer engagement and perceived presence by maintaining spatial coherence between virtual and real space. By activating architectural surfaces as part of the experience, the system repositions AR exhibitions as spatial narratives rather than conventional overlay-driven displays.

We propose SnapPhysics, a training-free framework that reconstructs 3D objects and estimates their physical properties such as mass, friction, and center of gravity from a single image. For physically coherent interactions in mixed reality (MR), such properties are as important as geometry. Prior approaches infer them by analyzing object dynamics in video, which is computationally costly, or by querying vision-language models (VLMs) on single images, which lacks geometric grounding and inter-object relationships. We address these limitations by combining instancelevel 3D reconstruction and spatial alignment with a physics-aware scene graph that encodes these relationships and per-object metric geometry as structured context for VLM-based property reasoning. Experiments on 3D-FRONT show that SnapPhysics improves scene-level F-Score by 18.6% over the best learning-based method, and on real captured scenes with ground-truth mass, it reduces the mean absolute log difference error (mALDE) by up to 20.5% and improves log-scale correlation (r2 ls) by up to 19.6% over VLM-only estimation. SnapPhysics enables physically interactive MR experiences without manual parameter tuning. Project page is https://snapphysics-ismar2026.github.io.

We present Mix3R, a training-free 3D scene reconstruction framework that enables immersive Mixed Reality (MR) interaction from a single real-world image. Despite recent progress in single-image 3D scene generation, existing methods often struggle with background recovery under occlusion and lack evaluations regarding natural interaction as well as immersion in MR environments. We address these challenges through a structured integration of diverse multi-task model priors, enabling geometrically consistent 3D scene reconstruction without additional training. The framework combines vision–language-guided foreground–background separation with depth alignment from back-projected point clouds to achieve reliable background completion while preserving detailed object geometry. Experiments on the 3D-FRONT dataset show that Mix3R improves reconstruction quality, reducing Chamfer Distance by over 23% and increasing object-level F-score by more than 6%, with additional gains in scene-level perceptual metrics. User studies on in-the-wild images further demonstrate higher user preference for the proposed method across diverse real-world scenes. These results indicate that our approach enables practical reconstruction of interactive MR spaces from an arbitrary single image. Our project page is https://mix3r2026.github.io