UnconFuse: Avatar Reconstruction from Unconstrained Images
Han Huang, Liliang Chen, Xihao Wang
TL;DR
UnconFuse introduces an improved 3D human body reconstruction method from unconstrained images, achieving top performance in the ECCV 2022 WCPA challenge by building on MVP-Human with specific enhancements.
Contribution
The paper presents an improved reconstruction approach tailored for unconstrained images, achieving first place in the ECCV 2022 WCPA challenge.
Findings
Achieved a score of 0.93 on the official test set.
Secured 1st place in the ECCV 2022 WCPA challenge.
Enhanced the MVP-Human baseline for better performance.
Abstract
The report proposes an effective solution about 3D human body reconstruction from multiple unconstrained frames for ECCV 2022 WCPA Challenge: From Face, Body and Fashion to 3D Virtual avatars I (track1: Multi-View Based 3D Human Body Reconstruction). We reproduce the reconstruction method presented in MVP-Human as our baseline, and make some improvements for the particularity of this challenge. We finally achieve the score 0.93 on the official testing set, getting the 1st place on the leaderboard.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Advanced Neural Network Applications · Medical Imaging Techniques and Applications