Search Results for author:
Found 7 papers, 2 papers with code
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories.
Enabling Visual Composition and Animation in Unsupervised Video Generation
We call our model CAGE for visual Composition and Animation for video GEneration.
Multi-View Unsupervised Image Generation with Cross Attention Guidance
The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-view images.
Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input.
Efficient Video Prediction via Sparsely Conditioned Flow Matching
We call our model Random frame conditioned flow Integration for VidEo pRediction, or, in short, RIVER.
Controllable Video Generation through Global and Local Motion Dynamics
We present GLASS, a method for Global and Local Action-driven Sequence Synthesis.
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
Moreover, we show that the Kalman Filter dynamical model for the evolution of the unknown parameters can be used to capture the gradient dynamics of advanced methods such as Momentum and Adam.
