Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Gangjian, Shu, Jian, Yu, Sicheng, Shen, Wenhao, Feng, Yu, Wang, Hao
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unify3D: An Augmented Holistic End-to-end Monocular 3D Human Reconstruction via Anatomy Shaping and Twins Negotiating
by: Yao, Nanjie, et al.
Published: (2025)

MultiGO++: Monocular 3D Clothed Human Reconstruction via Geometry-Texture Collaboration
by: Yao, Nanjie, et al.
Published: (2026)

SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction
by: Zhang, Gangjian, et al.
Published: (2025)

FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation
by: Shu, Jian, et al.
Published: (2025)

MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction
by: Zhang, Gangjian, et al.
Published: (2024)

SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
by: Shen, Wenhao, et al.
Published: (2025)

GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
by: Liu, Xinqi, et al.
Published: (2024)

Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video
by: Park, Pilseo, et al.
Published: (2025)

Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
by: Cheng, Chong, et al.
Published: (2025)

Expressive Gaussian Human Avatars from Monocular RGB Video
by: Hu, Hezhen, et al.
Published: (2024)

MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction
by: Dong, Zijian, et al.
Published: (2025)

Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction
by: Ren, Junlong, et al.
Published: (2025)

Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding
by: Ren, Junlong, et al.
Published: (2025)

Deblur-Avatar: Animatable Avatars from Motion-Blurred Monocular Videos
by: Luo, Xianrui, et al.
Published: (2025)

Reality's Canvas, Language's Brush: Crafting 3D Avatars from Monocular Video
by: Rao, Yuchen, et al.
Published: (2023)

DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
by: Chen, Yushuo, et al.
Published: (2025)

AvatarVTON: 4D Virtual Try-On for Animatable Avatars
by: Jiang, Zicheng, et al.
Published: (2025)

Multimodal Generation of Animatable 3D Human Models with AvatarForge
by: Liu, Xinhang, et al.
Published: (2025)

SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation
by: Choi, Yonwoo
Published: (2025)

3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
by: Zhao, Haoyu, et al.
Published: (2024)

MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos
by: Jin, Daisheng, et al.
Published: (2025)

Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video
by: Alghamdi, Eyad, et al.
Published: (2026)

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
by: Zhang, Jiawei, et al.
Published: (2024)

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video
by: Lee, Jeonghaeng, et al.
Published: (2026)

DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos
by: Shen, Wenhao, et al.
Published: (2026)

GGAvatar: Reconstructing Garment-Separated 3D Gaussian Splatting Avatars from Monocular Video
by: Chen, Jingxuan
Published: (2024)

InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
by: Budria, Alvaro, et al.
Published: (2024)

RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians
by: Peng, Sen, et al.
Published: (2025)

Capturing Head Avatar with Hand Contacts from a Monocular Video
by: He, Haonan, et al.
Published: (2025)

Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute
by: Gong, Chaoqun, et al.
Published: (2024)

MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video
by: Wang, Hongsheng, et al.
Published: (2024)

FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction
by: Fan, Jinlong, et al.
Published: (2025)

WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videos
by: Li, Hanhui, et al.
Published: (2026)

AR4D: Autoregressive 4D Generation from Monocular Videos
by: Zhu, Hanxin, et al.
Published: (2025)

D$^3$-Human: Dynamic Disentangled Digital Human from Monocular Video
by: Chen, Honghu, et al.
Published: (2025)

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation
by: Tu, Shuyuan, et al.
Published: (2025)

GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians
by: Wei, Xiaobao, et al.
Published: (2024)

AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection
by: Xu, Zhipei, et al.
Published: (2025)

ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation
by: Youwang, Kim, et al.
Published: (2026)

IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
by: Wang, Shaofei, et al.
Published: (2023)