3 Hits in 3.7 sec

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints [article]

Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang, Shunsuke Saito
2022 arXiv   pre-print
Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities.  ...  In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views.  ...  To avoid the ray-depth ambiguity, pixel-aligned neural fields [48, 51, 52, 69] attach spatial encoding to the pixel-aligned feature.  ... 
arXiv:2205.04992v2 fatcat:l756lhnexjh2pdb22aspwvc3bi

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering [article]

Youngjoong Kwon and Dahun Kim and Duygu Ceylan and Henry Fuchs
2021 arXiv   pre-print
In parallel, some work proposed to use pixel-aligned features to generalize radiance fields to arbitrary new scenes and objects.  ...  Moreover, a multi-view transformer is proposed to perform cross-attention between the temporally-fused features and the pixel-aligned features at each time step to integrate observations on the fly from  ...  Results of Pixel-Nerf [52] , PVA: Pixel-aligned volumetric avatar [36] and ours. Novel view synthesis on ZJU-MoCap.  ... 
arXiv:2109.07448v1 fatcat:lr7xzscnjbennf3fji2raapskq

Dagstuhl Reports, Volume 8, Issue 10, October 2018, Complete Issue [article]

We have volumetric understanding, knowing where we are etc 2.  ...  [T0-T4], use different aspects of PVA to perform these tasks, have different expectations on PVA, which in turn incur different properties of the UI in which they work with PVA.  ... 
doi:10.4230/dagrep.8.10 fatcat:q5uhtls46rd3zf4cnl4szgxc7y