by Hyungjun Doh | Oct 27, 2025 | 2025, Hyungjun Doh, Karthik Ramani, Sangpil Kim, Seunggeun Chi
We introduce a novel framework for reconstructing dynamic human-object interactions from monocular video that overcomes challenges associated with occlusions and temporal inconsistencies. Traditional 3D reconstruction methods typically assume static objects or full...
by Rahul Jain | Apr 25, 2025 | 2025, Augmented Reality, Featured Publications, Hyunggun Chi, Hyungjun Doh, Jingyu Shi, Karthik Ramani, Rahul Jain, Recent Publications, Seunggeun Chi
Context-aware AR instruction enables adaptive and in-situ learning experiences. However, hardware limitations and expertise requirements constrain the creation of such instructions. With recent developments in Generative Artificial Intelligence (Gen-AI), current...
by Seunggeun Chi | Feb 3, 2025 | 2025, Karthik Ramani, Sangpil Kim, Seunggeun Chi
Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D scenes using finite resources. These approaches create a 3D radiance field, parameterized by per-pixel 3D Gaussian...
by Seunggeun Chi | Sep 27, 2024 | 2024, Karthik Ramani, Recent Publications, Seunggeun Chi
We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands....
by Seunggeun Chi | Sep 26, 2024 | 2024, Featured Publications, Hyunggun Chi, Karthik Ramani, Karthik Ramani, Publications, Recent Publications, Seunggeun Chi
We introduce the Multi-Motion Discrete Diffusion Models (M2D2M), a novel approach for human motion generation from textual descriptions of multiple actions, utilizing the strengths of discrete diffusion models. This approach adeptly addresses the challenge of...
by Seunggeun Chi | Sep 18, 2024 | 2024, Hyunggun Chi, Karthik Ramani, Publications, Recent Publications, Seunggeun Chi
Skeleton-based action recognition has made significant advancements recently, with models like InfoGCN showcasing remarkable accuracy. However, these models exhibit a key limitation: they necessitate complete action observation prior to classification, which...
