5 papers
Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
Seunguk Do, Minwoo Huh, Joonghyuk Shin +1
Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses.…
SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency
Yeonsung Kim, Junggeun Do, Seunguk Do +3
3D human pose estimation (HPE) is characterized by intricate local and global dependencies among joints. Conventional supervised losses are limited in capturing these correlations…
MotionStream: Real-Time Video Generation with Interactive Motion Controls
Joonghyuk Shin, Zhengqi Li, Richard Zhang +4
Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present Mo…
Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
Joonghyuk Shin, Alchan Hwang, Yujin Kim +2
Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in st…
Tree-Guided Diffusion Planner
Hyeonseong Jeon, Cheolhong Min, Jaesik Park
Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. Standard gradient guidance typically performs optimally…