CVNov 18, 2022

UnconFuse: Avatar Reconstruction from Unconstrained Images

arXiv:2211.10098v13 citationsh-index: 22
Originality Synthesis-oriented
AI Analysis

This work addresses avatar reconstruction for computer vision applications, but it is incremental as it builds on an existing baseline with specific improvements for a challenge.

The paper tackled 3D human body reconstruction from multiple unconstrained images, achieving a score of 0.93 on the official testing set and securing first place in the ECCV 2022 WCPA Challenge.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes