A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
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
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  , PVA: Pixel-aligned volumetric avatar  and ours. Novel view synthesis on ZJU-MoCap. ...arXiv:2109.07448v1 fatcat:lr7xzscnjbennf3fji2raapskq
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