3D Face Reconstruction

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction
Apr 23, 2026Yisheng He, Steven Hoi3D Reconstruction 3D Avatar Generation
Tongyi Lab, Alibaba Group
Face Anything: 4D Face Reconstruction from Any Image Sequence
Apr 21, 2026Umut Kocasari, Simon Giebenhain, Richard Shaw +14D Reconstruction Deformable Shape Reconstruction
Technical University of Munich, Germany · Huawei Noah’s Ark Lab, London, UK
SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
Apr 21, 2026Bo Li, Jiahao Kang, Yubo Ma +43D Gaussian Splatting 3D Shape Editing
Shandong Technology and Business University · Nanchang Hangkong University · Institute of Computing Technology, Chinese Academy of Sciences +2
One-shot Compositional 3D Head Avatars with Deformable Hair
Apr 16, 2026Yuan Sun, Xuan Wang, WeiLi Zhang +3Human Avatar Animation 3D Face Reconstruction
Xi’an Jiaotong University, China
M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection
Apr 16, 2026Haotian Wu, Yue Cheng, Shan BianDeepfake Detection 3D Face Reconstruction
a College of Mathematics and Informatics, South China Agricultural University, Wushan 2026 Road, Tianhe District, Guangzhou, 510642, China
Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars
Apr 16, 2026Yicheng Gong, Jiawei Zhang, Liqiang Liu +6Disentangled Representation Learning 3D Avatar Generation
Nanjing University, Nanjing, China · Microsoft Research Asia, Beijing, China · University of Science and Technology of China, Hefei, China +1
One-Shot Feed-Forward 360 $^{\circ}$ Animatable Avatar via Inpainted UV-Space Gaussian Modeling
Jan 19, 2026Shuling Zhao, Dan Xu3D Gaussian Splatting 3D Reconstruction
The Hong Kong University of Science and Technology · Zeekr Automobile R&D Co., Ltd.
FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision
Nov 26, 2025Chen Ling, Henglin Shi, Hedvig Kjellström3D Morphable Models Monocular 3D Reconstruction
KTH Royal Institute of Technology, Sweden · Linköping University, Sweden
SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
Apr 19, 2025Chen Guo, Zhuo Su, Liao Wang +83D Gaussian Splatting 3D Asset Generation
Tsinghua Shenzhen International Graduate School, China · ByteDance and Pengcheng Lab, China · ByteDance, China +1
GNM Head: A Generative aNthropometric Model of the human head
Date pendingStylianos Ploumpis, Jan Bednarik, Gaspard Zoss +293D Morphable Models 3D Face Reconstruction
Google

Apr 23, 2026, cs.CVJ/K move · Enter open · S save

MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction

Yisheng He, Steven Hoi

Tongyi Lab, Alibaba Group

3D Reconstruction 3D Avatar Generation Deformable Shape Reconstruction Human Avatar Animation 3D Mesh Reconstruction 3D Face Reconstruction+2

Open paper AskPDF arXiv

We introduce MeshLAM, a feed-forward framework for one-shot animatable mesh head reconstruction that generates high-fidelity, animatable 3D head avatars from a single image. Unlike previous work that relies on time-consuming test-time optimization or extensive multi-view data, our method produces complete mesh representations with inherent animatability from a single image in a single forward pass. Our approach employs a dual shape and texture map architecture that simultaneously processes mesh vertices and texture map with extracted image features from a shared transformer backbone, allowing for coherent shape carving and appearance modeling. To prevent mesh collapse and ensure topological integrity during feed-forward deformation, we propose an iterative GRU-based decoding mechanism with progressive geometry deformation and texture refinement, coupled with a novel reprojection-based texture guidance mechanism that anchors appearance learning to the input image. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in reconstruction quality, animation capability, and computational efficiency. Project page at https://meshlam.github.io.

Momentum

Related topics

Latest papers 40