8 papers
Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
Hyunsoo Lee, Inwoo Hwang, Young Min Kim
Generating diverse, coherent, and plausible content from partially given inputs remains a fundamental challenge for diffusion models. Existing approaches face clear limitations: tr…
EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing
Inwoo Hwang, Donggeun Lim, Hojun Jang +1
With recent advances in embodied agents and AR devices, egocentric observations are readily available as input for real-world interactive online applications. However, egocentric v…
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
Inwoo Hwang, Hojun Jang, Bing Zhou +3
We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token…
Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene
Donggeun Lim, Jinseok Bae, Inwoo Hwang +3
In this work, we propose a framework that creates a lively virtual dynamic scene with contextual motions of multiple humans. Generating multi-human contextual motion requires holis…
SceneMI: Motion In-betweening for Modeling Human-Scene Interactions
Inwoo Hwang, Bing Zhou, Young Min Kim +2
Modeling human-scene interactions (HSI) is essential for understanding and simulating everyday human behaviors. Recent approaches utilizing generative modeling have made progress i…
Motion Synthesis with Sparse and Flexible Keyjoint Control
Inwoo Hwang, Jinseok Bae, Donggeun Lim +1
Creating expressive character animations is labor-intensive, requiring intricate manual adjustment of animators across space and time. Previous works on controllable motion generat…