A feed-forward pipeline predicts 3D human Gaussian splats from two input images (front and back) in 190 ms, using a DUSt3R-style point cloud predictor with extra side-view heads, nearest-neighbor color warping, and a Gaussian attribute regression network.
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We present a method that enables synthesizing novel views and novel poses of arbitrary human performers from sparse multi-view images. A key ingredient of our method is a hybrid appearance blending module that combines the advantages of the implicit body NeRF representation and image-based rendering. Existing generalizable human NeRF methods that are conditioned on the body model have shown robustness against the geometric variation of arbitrary human performers. Yet they often exhibit blurry results when generalized onto unseen identities. Meanwhile, image-based rendering shows high-quality results when sufficient observations are available, whereas it suffers artifacts in sparse-view settings. We propose Neural Image-based Avatars (NIA) that exploits the best of those two methods: to maintain robustness under new articulations and self-occlusions while directly leveraging the available (sparse) source view colors to preserve appearance details of new subject identities. Our hybrid design outperforms recent methods on both in-domain identity generalization as well as challenging cross-dataset generalization settings. Also, in terms of the pose generalization, our method outperforms even the per-subject optimized animatable NeRF methods. The video results are available at https://youngjoongunc.github.io/nia
citation-role summary
citation-polarity summary
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds
A feed-forward pipeline predicts 3D human Gaussian splats from two input images (front and back) in 190 ms, using a DUSt3R-style point cloud predictor with extra side-view heads, nearest-neighbor color warping, and a Gaussian attribute regression network.