7 papers
Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction
Hongkun Dou, Zike Chen, Fengji Li +2
Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we present \underline{\textbf{G}}…
Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction
Shaohua Liu, Ning Gao, Zuoya Gu +3
Reconstructing realistic underwater scenes from underwater video remains a meaningful yet challenging task in the multimedia domain. The inherent spatiotemporal degradations in und…
Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes
Hongkun Dou, Zike Chen, Zeyu Li +3
Diffusion models have gained prominence as powerful generative tools for solving inverse problems due to their ability to model complex data distributions. However, existing method…
DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
Junzhe Lu, Jing Lin, Hongkun Dou +8
We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent…
Global Modeling Matters: A Fast, Lightweight and Effective Baseline for Efficient Image Restoration
Xingyu Jiang, Ning Gao, Hongkun Dou +4
Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution…
You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
Hongkun Dou, Zeyu Li, Xingyu Jiang +4
Diffusion models (DMs) have recently demonstrated remarkable success in modeling large-scale data distributions. However, many downstream tasks require guiding the generated conten…