While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they often fail to respect fundamental physical dynamics. Although recent physics-constrained methods incorporate explicit dynamics priors to improve physical plausibility, th...
Hao-Ran Qin, Ren-Rong Wu, Tian-Yu Huang et al.· 0 citations
ZoomDiff is proposed, a high-fidelity diffusion model that leverages dual-camera inputs in both latent and pixel spaces for photo-realistic transitions that outperforms state-of-the-art methods quantitatively and qualitatively.
Jia-Yi Zhang, Ren-Rong Wu, Yu-Kang Ding et al.· 0 citations
4DHumanDiff is presented, a diffusion framework that directly generates dynamic humans represented by 4D Gaussian Splatting from text prompts and achieves better temporal and multi-view consistency, and reduces inference time by more than 10x.
This work proposes GS-RealBlur, a data acquisition framework for real-world image deblurring, achieving both blur realism and acquisition flexibility, and introduces a Blur-aware Pose Refinement (BPR) module that refines the pose using appearance consistency and centroid alignment constraints.
Mingyang Chen, Zhilu Zhang, Honglei Xu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
