Skip to yearly menu bar Skip to main content


Cinematic Behavior Transfer via NeRF-based Differentiable Filming

Xuekun Jiang · Anyi Rao · Jingbo Wang · Dahua Lin · Bo Dai

Arch 4A-E Poster #187
[ ]
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT


In the evolving landscape of digital media and video production, the precise manipulation and reproduction of visual elements like camera movements and character actions are highly desired. Existing SLAM methods face limitations in dynamic scenes and human pose estimation often focuses on 2D projections, neglecting 3D statuses. To address these issues, we first introduce a reverse filming behavior estimation technique. It optimizes camera trajectories by leveraging NeRF as a differentiable renderer and refining SMPL tracks. We then introduce a cinematic transfer pipeline that is able to transfer various shot types to a new 2D video or a 3D virtual environment. The incorporation of 3D engine workflow enables superior rendering and control abilities, which also achieves a higher rating in the user study.

Live content is unavailable. Log in and register to view live content