Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative by specifying tasks in-context, it remains restricted to the image domain. To explore whether analogy-based methods can unify diverse video tasks and generalize to out...
Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan et al.· 0 citations
Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative by specifying tasks in-context, it remains restricted to the image domain. To explore whether analogy-based methods can unify diverse video tasks and generalize to out...
Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan et al.· 0 citations
Semantic Motion Graph (SMG), a novel approach models the Gaussian motion as the low-rank semantic motion, which achieves state-of-the-art performance on monocular dynamic Gaussian splatting across challenging real-world benchmarks.
Hao-Zheng Yu, Xinyi Yang, Run-Dong Luo et al.· 0 citations
UniD is introduced, a unified video model that jointly predicts eight dense scene properties-depth, surface normals, semantic segmentation, boundaries, human parts, albedo, shading, and materials-all learned from disjoint, domain-specific datasets.
