Researchers from the University of Washington and Google develop Deformable Neural Radiance Fields (D-NeRF) that can turn casually captured selfie photos/videos into photorealistic renderings of the subject from arbitrary viewpoints, dubbed "nerfies". The paper "Deformable Neural Radiance Fields" is authored by Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla.
We present the first method capable of photorealistically reconstructing a non-rigidly deforming scene using photos/videos captured casually from mobile phones. Our approach -- D-NeRF -- 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 D-NeRF 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 data using a rig with two mobile phones that take time-synchronized photos, 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.