Skip to yearly menu bar Skip to main content


Flow Supervision for Deformable NeRF

Chaoyang Wang · Lachlan Ewen MacDonald · László A. Jeni · Simon Lucey

West Building Exhibit Halls ABC 050
award Highlight
[ ] [ Project Page ]


In this paper we present a new method for deformable NeRF that can directly use optical flow as supervision. We overcome the major challenge with respect to the computationally inefficiency of enforcing the flow constraints to the backward deformation field, used by deformable NeRFs. Specifically, we show that inverting the backward deformation function is actually not needed for computing scene flows between frames. This insight dramatically simplifies the problem, as one is no longer constrained to deformation functions that can be analytically inverted. Instead, thanks to the weak assumptions required by our derivation based on the inverse function theorem, our approach can be extended to a broad class of commonly used backward deformation field. We present results on monocular novel view synthesis with rapid object motion, and demonstrate significant improvements over baselines without flow supervision.

Chat is not available.