search

YuliangXiu / ECON

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
https://xiuyuliang.cn/econ
Other
1.11k stars 107 forks source link

Suggestion: Multi-view inputs #50

Closed anwoflow closed 1 year ago

anwoflow commented 1 year ago

Would it be possible, given multi-view input (even 2-3 sides, poses) to have the model optimize for a 'consensus' mesh and texture? Especially given the occlusion for a single POV, there are many blindspots, so the confidence level for different parts of the texture should be very different.

YuliangXiu commented 1 year ago

ECON does not support multi-view right now, but it should work like original PIFu's multi-view version [1]

[1] Saito S, Huang Z, Natsume R, et al. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization[C], Proceedings of the IEEE/CVF international conference on computer vision. 2019: 2304-2314.

YuliangXiu commented 1 year ago

@anwoflow

We recently released a new work, TeCH. Given a single image, TeCH could produce a full textured avatar with both intricate geometric details and consistent high-quality texture.

Homepage: https://huangyangyi.github.io/TeCH/ Code: https://github.com/huangyangyi/TeCH