paper-with-me

홈 › Papers

MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space

2024-04-01 · Armand Comas-Massagué, Di Qiu, Menglei Chai, Marcel Bühler, Amit Raj, Ruiqi Gao, Qiangeng Xu, Mark Matthews, Paulo Gotardo, Octavia Camps, Sergio Orts-Escolano, Thabo Beeler

We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization. Central to our approach are key innovations aimed at overcoming the challenges in photo-realistic avatar synthesis. Firstly, we utilize a conditional Neural Radiance Fields (NeRF) model, trained on a large-scale unannotated multi-view dataset, to create a versatile initial solution space that accelerates and diversifies avatar generation. Secondly, we develop a geometric prior, leveraging the capabilities of Text-to-Image Diffusion Models, to ensure superior view invariance and enable direct optimization of avatar geometry. These foundational ideas are complemented by our optimization pipeline built on Variational Score Distillation (VSD), which mitigates texture loss and over-saturation issues. As supported by our extensive experiments, these strategies collectively enable the creation of custom avatars with unparalleled visual quality and better adherence to input text prompts. You can find more results and videos in our website: https://syntec-research.github.io/MagicMirror

📄 PDF Abstract BibTeX arXiv:2404.01296

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation

2025-09-12 · Jia Wang, Jie Hu, Xiaoqi Ma, Hanghang Ma 외 arxiv

Text-to-image (T2I) generation has achieved remarkable progress in instruction following and aesthetics. However, a persistent challenge is the prevalence of physical artifacts, such as anatomical and structural flaws, w…

Text-to-Image GenerationInstruction Following

Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image

2026-04-15 · Yujie Gao, Yao Xiao, Xiangnan Zhu, Ya Li 외 arxiv

Reconstructing a complete 3D head from a single portrait remains challenging because existing methods still face a sharp quality-speed trade-off: high-fidelity pipelines often rely on multi-stage processing and per-subje…

FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers

2025-08-27 · Yue Wu, Xuanhong Chen, Yufan Wu, Wen Li 외 arxiv

Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar fram…

Instant 3D Human Avatar Generation using Image Diffusion Models

2024-06-11 · Nikos Kolotouros, Thiemo Alldieck, Enric Corona, Eduard Gabriel Bazavan 외

We present AvatarPopUp, a method for fast, high quality 3D human avatar generation from different input modalities, such as images and text prompts and with control over the generated pose and shape. The common theme is …

3D GenerationImage Generation

AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars

2026-07-27 · Hengyuan Zhang, Jingna Sun, Meiguang Jin, Junfeng Ma arxiv

Production-ready audio-driven avatar generation requires efficient inference without sacrificing fidelity or motion expressiveness. However, existing acceleration methods often compromise quality through restrictive arch…

Video Generation