Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
This addresses the challenge of sparse image coverage or ambiguous poses in computer vision and graphics by integrating camera trajectory prediction and video generation into a single model.
The paper tackles the problem of separating camera parameter recovery and novel view rendering by proposing Rays as Pixels, a Video Diffusion Model that learns a joint distribution over videos and camera trajectories, enabling tasks like predicting camera trajectories from video and generating video from input images along target trajectories, with results reported on pose estimation and camera-controlled video generation.
Recovering camera parameters from images and rendering scenes from novel viewpoints have long been treated as separate tasks in computer vision and graphics. This separation breaks down when image coverage is sparse or poses are ambiguous, since each task needs what the other produces. We propose Rays as Pixels, a Video Diffusion Model (VDM) that learns a joint distribution over videos and camera trajectories. We represent each camera as dense ray pixels (raxels) and denoise them jointly with video frames through Decoupled Self-Cross Attention mechanism. A single trained model handles three tasks: predicting camera trajectories from video, jointly generating video and camera trajectory from input images, and generating video from input images along a target camera trajectory. Because the model can both predict trajectories from a video and generate views conditioned on its own predictions, we evaluate it through a closed-loop self-consistency test, demonstrating that its forward and inverse predictions agree. Notably, trajectory prediction requires far fewer denoising steps than video generation, even a few denoising steps suffice for self-consistency. We report results on pose estimation and camera-controlled video generation.