CompAvatar: 3D Human Avatar Reconstruction From Partial‐View Monocular Video by Semantic‐Guided View Generation

ABSTRACT Reconstructing 3D human avatars from monocular video typically faces the challenge of appearance collapse caused by incomplete observation. Existing methods commonly utilise pretrained image diffusion models as generative priors, distilling structural and texture knowledge to supervise 3D generation. However, these priors often struggle to recover subject‐specific details, and injecting them comes at the cost of distorting observed regions. To address these issues, this paper presents a dual‐branch framework, termed CompAvatar, which can generate and fuse semantically consistent views in missing observations for improved 3D avatar integrity. Specifically, an observation modelling branch reconstructs coarse 3D Gaussians to guide the view augmentation branch. To address the challenge of refining appearance without distorting observed regions within view augmentation, CompAvatar introduces three modules. First, to ensure semantic consistency, the component semantic learning module extracts fine‐grained components from video to fine‐tune a personalised view generator, capturing specific‐subject appearance. Subsequently, to restore details while protecting observed regions, the localised view refinement module employs component‐level anomaly detection to locate defect masks for view generation. Finally, the spatial consistency distillation strategy leverages 3D spatial consistency to progressively feed generated views back into the 3D representation. Experiments show CompAvatar outperforms existing methods in restoring missing details from partial‐view monocular videos.

Authors

Institutions

Publication Details

Journal
CAAI Transactions on Intelligence Technology
Published
2026-11-13
DOI
https://doi.org/10.1049/cit2.70197
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

CompAvatar: 3D Human Avatar Reconstruction From Partial‐View Monocular Video by Semantic‐Guided View Generation

Lei Meng, Manyi Li, Lei Wu, Xiang Li et al.
CAAI Transactions on Intelligence Technology
3D Shape Modeling and Analysis
article

CompAvatar: 3D Human Avatar Reconstruction From Partial‐View Monocular Video by Semantic‐Guided View Generation

Lei Meng, Manyi Li, Lei Wu, Xiang Li, Xiangxu Meng
article en

Abstract

ABSTRACT Reconstructing 3D human avatars from monocular video typically faces the challenge of appearance collapse caused by incomplete observation. Existing methods commonly utilise pretrained image diffusion models as generative priors, distilling structural and texture knowledge to supervise 3D generation. However, these priors often struggle to recover subject‐specific details, and injecting them comes at the cost of distorting observed regions. To address these issues, this paper presents a dual‐branch framework, termed CompAvatar, which can generate and fuse semantically consistent views in missing observations for improved 3D avatar integrity. Specifically, an observation modelling branch reconstructs coarse 3D Gaussians to guide the view augmentation branch. To address the challenge of refining appearance without distorting observed regions within view augmentation, CompAvatar introduces three modules. First, to ensure semantic consistency, the component semantic learning module extracts fine‐grained components from video to fine‐tune a personalised view generator, capturing specific‐subject appearance. Subsequently, to restore details while protecting observed regions, the localised view refinement module employs component‐level anomaly detection to locate defect masks for view generation. Finally, the spatial consistency distillation strategy leverages 3D spatial consistency to progressively feed generated views back into the 3D representation. Experiments show CompAvatar outperforms existing methods in restoring missing details from partial‐view monocular videos.

CAAI Transactions on Intelligence Technology
Shandong University (CN)
3D Shape Modeling and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon