The recent advancements in 3D and 4D generative modeling have shown significant progress in creating high-fidelity, detailed, and interactive 3D assets. Researchers are focusing on developing models that not only generate realistic 3D objects but also handle the complexities of object deformations over time, as seen in 4D modeling. The integration of multi-modal inputs, such as sketches and voice commands, into 3D generation pipelines is enhancing user interaction and creativity in extended reality (XR) environments. Additionally, the scalability of mesh generation models has reached new heights, allowing for the creation of artist-like 3D meshes with unprecedented resolution and fidelity. These developments are poised to revolutionize industries such as animation, gaming, and virtual environments by providing tools that are both efficient and user-friendly.

Noteworthy papers include:

• DNF for its innovative dictionary-based approach to 4D generative modeling.
• MS2Mesh-XR for its multi-modal sketch-to-mesh generation in XR environments.
• Meshtron for its high-fidelity, scalable 3D mesh generation.