Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Personalized 3D avatar editing holds significant promise due to its user-friendliness and availability to applications such as AR/VR and virtual try-ons. Previous studies have explored the feasibility of 3D editing, but often struggle to generate visually pleasing results, possibly due to the unstable representation learning under mixed optimization of geometry and texture in complicated reconstructed scenarios. In this paper, we aim to provide an accessible solution for ordinary users to create their editable 3D avatars with precise region localization, geometric adaptability, and photorealistic renderings. To tackle this challenge, we introduce a meticulously designed framework that decouples the editing process into local spatial adaptation and realistic appearance learning, utilizing a hybrid Tetrahedron-constrained Gaussian Splatting (TetGS) as the underlying representation. TetGS combines the controllable explicit structure of tetrahedral grids with the high-precision rendering capabilities of 3D Gaussian Splatting and is optimized in a progressive manner comprising three stages: 3D avatar instantiation from real-world monocular videos to provide accurate priors for TetGS initialization; localized spatial adaptation with explicitly partitioned tetrahedrons to guide the redistribution of Gaussian kernels; and geometry-based appearance generation with a coarse-to-fine activation strategy. Both qualitative and quantitative experiments demonstrate the effectiveness and superiority of our approach in generating photorealistic 3D editable avatars.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 72 of its 84 references that are in the map. First posted on arXiv 29 Apr 2025.
Builds on
72 of 84 references.
References · 72
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2023GPT-4 Technical Reportcited by 18,396
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023Segment Anythingcited by 8,234
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
- 2021Zero-Shot Text-to-Image Generationcited by 4,288
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
38 more
- 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
- 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
- 2020Implicit Geometric Regularization for Learning Shapescited by 710
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
- 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
- 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
- 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
- 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
- 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
- 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 304
- 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
- 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
- 2019Self-Correction for Human Parsingcited by 180
- 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 168
- 2023DreamEditor: Text-Driven 3D Scene Editing with Neural Fieldscited by 155
- 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
- 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 123
- 2023Delta Denoising Scorecited by 121
- 2023TADA! Text to Animatable Digital Avatarscited by 110
- 2024Improving Diffusion Models for Authentic Virtual Try-on in the Wildcited by 109
- 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
- 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
- 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
- 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
- 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generationcited by 88
- 2023DreamWaltz: Make a Scene with Complex 3D Animatable Avatarscited by 82
- 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
50 most cited of 72 All 72 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.