mlsanityData to 7 Oct 2026

LUCAS: Layered Universal Codec Avatars

arXiv 2502.19739 ↗First posted 27 Feb 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation. Unlike previous UPMs that treat hair as an integral part of the head, our approach separates the modeling of the hairless head and hair into distinct branches. LUCAS is the first to introduce a mesh-based UPM, facilitating real-time rendering on devices. Our layered representation also improves the anchor geometry for precise and visually appealing Gaussian renderings. Experimental results indicate that LUCAS outperforms existing single-mesh and Gaussian-based avatar models in both quantitative and qualitative assessments, including evaluations on held-out subjects in zero-shot driving scenarios. LUCAS demonstrates superior dynamic performance in managing head pose changes, expression transfer, and hairstyle variations, thereby advancing the state-of-the-art in 3D head avatar reconstruction.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 39 of its 66 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

39 of 66 references.

References · 39

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2016HyperNetworkscited by 1,003
  5. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  6. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  7. 2018Deep Appearance Models for Face Renderingcited by 164
  8. 2023Relightable Gaussian Codec Avatarscited by 126
  9. 2021Pixel Codec Avatarscited by 125
  10. 2023Improving Tuning-Free Real Image Editing with Proximal Guidancecited by 87
  11. 2023LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatarcited by 50
  12. 2020Audio- and Gaze-driven Facial Animation of Codec Avatarscited by 46
27 more
  1. 2022A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmarkcited by 45
  2. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  3. 2024URAvatar: Universal Relightable Gaussian Codec Avatarscited by 43
  4. 2021PVA: Pixel-aligned Volumetric Avatarscited by 40
  5. 2023Text-Guided Generation and Editing of Compositional 3D Avatarscited by 39
  6. 2023HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modelingcited by 35
  7. 2023Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentationcited by 32
  8. 2022NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animationcited by 30
  9. 2021HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capturecited by 29
  10. 2023MEGANE: Morphable Eyeglass and Avatar Networkcited by 24
  11. 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Videocited by 24
  12. 2019Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoderscited by 22
  13. 2024LayGA: Layered Gaussian Avatars for Animatable Clothing Transfercited by 22
  14. 2022TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformerscited by 21
  15. 2024GALA: Generating Animatable Layered Assets from a Single Scancited by 21
  16. 2020Expressive Telepresence via Modular Codec Avatarscited by 17
  17. 2022DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Methodcited by 17
  18. 2024Rasterized Edge Gradients: Handling Discontinuities Differentiablycited by 14
  19. 2024Layout Agnostic Scene Text Image Synthesis with Diffusion Modelscited by 14
  20. 2022Region Proposal Rectification Towards Robust Instance Segmentation of Biological Imagescited by 13
  21. 2025Improved Training Technique for Latent Consistency Modelscited by 13
  22. 2019Synthesizing facial photometries and corresponding geometries using generative adversarial networkscited by 11
  23. 2023Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillationcited by 11
  24. 2023DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Imagecited by 11
  25. 2023Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistencycited by 5
  26. 2023HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMscited by 5
  27. 2024Instantaneous Perception of Moving Objects in 3Dcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatarscited by 7
  2. 2025STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstructioncited by 3
  3. 2026Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretrainingcited by 3
  4. 2025SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Haircited by 2
  5. 2025Large Sign Language Models: Toward 3D American Sign Language Translationcited by 1
  6. 2025FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpointcited by 1
  7. 2026AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Texturescited by 0