AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors

TL;DR

AHOY introduces a novel pipeline for reconstructing complete, animatable 3D Gaussian avatars from occluded monocular videos by leveraging diffusion models, canonical-to-pose architecture, and decoupled supervision, achieving state-of-the-art results.

Contribution

The paper presents a new method combining diffusion-based hallucination, a two-stage architecture, and decoupled supervision to handle occlusion in 3D avatar reconstruction from monocular videos.

Findings

State-of-the-art reconstruction quality on occluded YouTube videos

Robust avatar animation with novel poses

Effective handling of multi-view inconsistencies

Abstract

We present AHOY, a method for reconstructing complete, animatable 3D Gaussian avatars from in-the-wild monocular video despite heavy occlusion. Existing methods assume unoccluded input-a fully visible subject, often in a canonical pose-excluding the vast majority of real-world footage where people are routinely occluded by furniture, objects, or other people. Reconstructing from such footage poses fundamental challenges: large body regions may never be observed, and multi-view supervision per pose is unavailable. We address these challenges with four contributions: (i) a hallucination-as-supervision pipeline that uses identity-finetuned diffusion models to generate dense supervision for previously unobserved body regions; (ii) a two-stage canonical-to-pose-dependent architecture that bootstraps from sparse observations to full pose-dependent Gaussian maps; (iii) a map-pose/LBS-pose decoupling that absorbs multi-view inconsistencies from the generated data; (iv) a head/body split supervision strategy that preserves facial identity. We evaluate on YouTube videos and on multi-view capture data with significant occlusion and demonstrate state-of-the-art reconstruction quality. We also demonstrate that the resulting avatars are robust enough to be animated with novel poses and composited into 3DGS scenes captured using cell-phone video. Our project page is available at https://miraymen.github.io/ahoy/