Nerfies: Deformable Neural Radiance Fields
This work addresses the challenge of creating photorealistic 3D models of deformable subjects from casual mobile phone captures, which is significant for applications like virtual reality and content creation.
This paper introduces a method for photorealistically reconstructing deformable scenes from casually captured mobile phone photos/videos. It achieves this by augmenting neural radiance fields (NeRF) with a continuous volumetric deformation field, enabling high-fidelity renderings of subjects from arbitrary viewpoints.
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones. Our approach augments neural radiance fields (NeRF) by optimizing an additional continuous volumetric deformation field that warps each observed point into a canonical 5D NeRF. We observe that these NeRF-like deformation fields are prone to local minima, and propose a coarse-to-fine optimization method for coordinate-based models that allows for more robust optimization. By adapting principles from geometry processing and physical simulation to NeRF-like models, we propose an elastic regularization of the deformation field that further improves robustness. We show that our method can turn casually captured selfie photos/videos into deformable NeRF models that allow for photorealistic renderings of the subject from arbitrary viewpoints, which we dub "nerfies." We evaluate our method by collecting time-synchronized data using a rig with two mobile phones, yielding train/validation images of the same pose at different viewpoints. We show that our method faithfully reconstructs non-rigidly deforming scenes and reproduces unseen views with high fidelity.