TL;DR
This paper presents an innovative method that leverages user-specified action paths to guide the 4D scene generation that dynamically synchronizes motions in the action path domain with their corresponding contents in the time domain.
AniGS is presented, a method for scene-level animation of 3D Gaussian Splatting (3DGS) reconstructions that adds subtle, distributed dynamics, e.g., vegetation motion, while preserving rigid structures in reconstructed environments.
This work proposes a framework known as Video-Generation Environment Representation (VGER), which leverages the advances of large-scale video generation models to generate a moving camera video conditioned on the input image, and demonstrates its ability to produce smooth motions that account for the captured geometry of a scene, all from a single RGB input image.
This paper proposes a semantics-guided scene decoupling module that separates Gaussian primitives into static and dynamic components based on motion vectors, and introduces a motion-aware densification module for motion compensation, which alleviates the incomplete rendering of dynamic objects caused by insufficient spatio-temporal information.
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 images or frames.
This work shows that camera motion, object trajectories, and depth can be unified into a single 3D point-track representation, from which one model performs joint camera and object control, depth editing, and motion transfer in a single forward pass, enabling interactive 4D-controllable streaming generation for the first time.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
