Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating not only a visually constrained hand pose but also a control target that stabilizes the grasp. Existing methods either model only visual hand...
Han Jiang, E. Vouga, Qi-Xing Huang et al.· 0 citations
Forecasting future 3D occupancy from surround-view cameras is essential for autonomous driving, yet existing approaches rely on dense voxel or bird's-eye-view representations whose cost grows rapidly with spatial resolution and prediction horizon. Because these representations do not explicitly maintain object identiti...
Hwanhee Jung, SeungHyeon Kim, Inkyu Koo et al.· 0 citations
Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable cost, to condition on a source video and an editing instruction. In this report we explore a different route and show that a strong instruction-based image editing model...
Yun-Peng Bai, Yossi Gandelsman, Michael Gharbi et al.· 3 citations
This paper investigates the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels and finds that the optimization of the spectral alignment objective is in an equivalent form of diffusion score distillation in the represe...
Yuehao Wang, Peihao Wang, Hanwen Jiang et al.· 0 citations
This work revisits the role of positional encoding in video diffusion transformers and shows that it provides a useful spatial bias for geometry-aware control, and introduces a geometry-aware cross-attention mechanism that enables target video latent tokens to attend to structured context tokens derived from reference...
