MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
This work addresses the need for scalable training data and flexible task design in robotics by enabling interactive and editable 4D world simulation, representing an incremental improvement over existing text-to-video models.
The authors tackled the problem of generating controllable and editable 4D scenes for robotics applications, introducing MorphoSim, a language-guided framework that produces dynamic environments with multi-view consistency and object-level controls, achieving high scene fidelity.
World models that support controllable and editable spatiotemporal environments are valuable for robotics, enabling scalable training data, repro ducible evaluation, and flexible task design. While recent text-to-video models generate realistic dynam ics, they are constrained to 2D views and offer limited interaction. We introduce MorphoSim, a language guided framework that generates 4D scenes with multi-view consistency and object-level controls. From natural language instructions, MorphoSim produces dynamic environments where objects can be directed, recolored, or removed, and scenes can be observed from arbitrary viewpoints. The framework integrates trajectory-guided generation with feature field dis tillation, allowing edits to be applied interactively without full re-generation. Experiments show that Mor phoSim maintains high scene fidelity while enabling controllability and editability. The code is available at https://github.com/eric-ai-lab/Morph4D.