BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
This addresses the challenge of generating complex, large-scale 3D scenes for applications like virtual environments or simulation, representing an incremental advance over existing 3D object synthesis techniques.
The paper tackles the problem of generating large-scale 3D scenes by proposing BerfScene, a method that uses BEV-conditioned equivariant radiance fields, enabling manipulation via BEV maps and stitching local scenes into infinite-scale scenes with smooth consistency, as demonstrated through extensive experiments on 3D scene datasets.
Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis technique since 3D scenes usually hold complex spatial configurations and consist of a number of objects at varying scales. We thus propose a practical and efficient 3D representation that incorporates an equivariant radiance field with the guidance of a bird's-eye view (BEV) map. Concretely, objects of synthesized 3D scenes could be easily manipulated through steering the corresponding BEV maps. Moreover, by adequately incorporating positional encoding and low-pass filters into the generator, the representation becomes equivariant to the given BEV map. Such equivariance allows us to produce large-scale, even infinite-scale, 3D scenes via synthesizing local scenes and then stitching them with smooth consistency. Extensive experiments on 3D scene datasets demonstrate the effectiveness of our approach. Our project website is at https://zqh0253.github.io/BerfScene/.