Reconstructing dynamic scenes from sparse multi-view videos remains challenging due to insufficient geometric constraints, scene motion, and changing visibility. While temporal modeling captures scene dynamics, it does not resolve geometric ambiguities arising from limited multi-view observations. We present a geometry...
Yun-Qi Gao, Zhan-Feng Liao, Jia-Jun Zhang et al.· 0 citations
Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either rely on computationally expensive optimization or require calibrated cameras and low-resolution inputs, making real-time high-resolution deployment impractical. In this w...
Han-Zhang Tu, Zhan-Feng Liao, Wei Min et al.· 0 citations
D3GS is proposed, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance and injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation.
Yun-Qi Gao, Zhan-Feng Liao, Han-Zhang Tu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.