From the 1 of 8 linked papers with an AI index.
8 papers
AtlasLC: Fast Codec-Ready Compression of Object-Centric 3D Gaussian Splatting
ByungHyun Kim, Jinwoo Jeon, Woontack Woo
AtlasLC is a source‑free, training‑free pipeline that quickly compresses object‑centric 3D Gaussian Splatting assets for XR, cutting preparation and compression time while preservi…
DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors
Seok-Young Kim, Abdelrahman Elskhawy, Taewook Ha +4
We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct reliable…
Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality
Taewook Ha, Woojin Cho, Dooyoung Kim +1
We propose Int3DNet, a scene-aware network that predicts 3D intention areas directly from scene geometry and head-hand motion cues, enabling robust human intention prediction witho…
Task Breakpoint Generation using Origin-Centric Graph in Virtual Reality Recordings for Adaptive Playback
Selin Choi, Dooyoung Kim, Taewook Ha +2
We propose a method for generating task breakpoints based on an Origin-Centric Graph (OCG) to segment goal-oriented activity recordings into task units for adaptive playback in Vir…
Viewpoint-Tolerant Depth Perception for Shared Extended Space Experience on Wall-Sized Display
Dooyoung Kim, Jinseok Hong, Heejeong Ko +1
We proposed viewpoint-tolerant shared depth perception without individual tracking by leveraging human cognitive compensation in universally 3D rendered images on a wall-sized disp…
Spatio-Temporal Mixed and Augmented Reality Experience Description for Interactive Playback
Dooyoung Kim, Woontack Woo
We propose the Spatio-Temporal Mixed and Augmented Reality Experience Description (MAR-ED), a novel framework to standardize the representation of past events for interactive and a…