These target videos may vary widely in complexity of scenes, activities, camera trajectory, etc.

Despitethehighdemand,high-quality 3D content remains relatively scarce.

We present a method for text-driven perpetual view generation - synthesizing long-term videos of various scenes solely from an input text prompt describing the scene and camera poses.

We propose ChatCam, a system that allows users to control camera operations through natural language interaction.

Indoor tasks are heavily related to human activities.

Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction.