TL;DR
The UniCam framework is proposed, a unified framework that introduces a temporally coherent stochastic representation, termed CameraNoise, warped from camera intrinsic and extrinsic parameters, which significantly outperforms prior methods in both fidelity and controllability.
CameraAnything is introduced, the first unified framework for camera controlled video editing that enables joint control of both intrinsic and extrinsic camera parameters, and a scalable synthetic pipeline is developed that constructs diverse dynamic scenes through structured multi-camera recording and generates synchr...
UniWorld-View is introduced, a unified framework for controllable large-baseline novel view synthesis from monocular inputs that integrates explicit 3D guidance with generative diffusion modeling to enable precise camera control and geometrically consistent view generation.
This work proposes CameraSquad, a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory generation, and designs a dual-mode cross-view attention mechanism that maintains consistency across parallel trajectories while guaranteeing camera control precision.
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...
Despite the success of diffusion models in Video Frame Interpolation (VFI), existing methods still suffer from two critical limitations. First, latent diffusion inevitably loses fine-grained details when reconstructing images from latent representations back to the pixel space. Second, multi-step sampling incurs prohib...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
