neuman

We have hosted the application neuman in order to run this application in our online workstations with Wine or directly.

Quick description about neuman:

NeuMan is a reference implementation that reconstructs both an animatable human and its background scene from a single monocular Video using neural radiance fields. It supports novel view and novel pose synthesis, enabling compositional results like transferring reconstructed humans into new scenes. The pipeline separates human/body and environment, learning consistent geometry and appearance to support animation. Demos showcase sequences such as dance and handshake, and the code provides guidance for running evaluations and rendering. As a research release, it serves both as a baseline and as a starting point for work on human-centric NeRFs. The emphasis is on practical reconstruction quality from minimal capture setups. Compositional outputs to blend humans and backgrounds. Novel view and novel pose synthesis from learned radiance fields.

Features:

• Single-Video reconstruction of scene plus animatable human
• Baseline for human-centric NeRF research and applications
• Separation of human and environment for better control
• Reference code and demos for reproduction
• Novel view and novel pose synthesis from learned radiance fields
• Compositional outputs to blend humans and backgrounds

Programming Language: Python.
Categories: