Research map / 3D vision / Face and shape
Generative textures for 3D humans
Synthesizes editable textures and disentangled geometry-appearance using adversarial and neural rasterization.
27 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Face and shape, keyword cluster “avatar · human · body”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
8 papers in 2023–24 and 10 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 2.2% to 2.7%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2018 · Texture Mapping for 3D Reconstruction With RGB-D Sensor (CVPR 2018 · 98 citations)
- 2019 · X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks (CVPR 2019 · 253 citations)
- 2020 · SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans (CVPR 2020 · 145 citations)
- 2021 · View Generalization for Single Image Textured 3D Models (CVPR 2021 · 24 citations)
- 2022 · Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images (CVPR 2022 · 36 citations)
- 2023 · Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars (CVPR 2023 · 97 citations)
- 2024 · Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024 · 64 citations)
- 2025 · Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · 5 citations)
- 2026 · Condition Matters in Full-head 3D GANs (ICLR 2026 · 0 citations)
Earliest papers here
- Texture Mapping for 3D Reconstruction With RGB-D Sensor (CVPR 2018 · 98 citations)
- X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks (CVPR 2019 · 253 citations)
- SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans (CVPR 2020 · 145 citations)
What has been tried
22 papers here report 205 measured changes (a component added, removed or swapped, compared with a baseline): helped 76%, no clear effect 4%, hurt 20%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add the coarse stage before UV refinement | Text-to-texture · FID | 48.81 -> 27.28 | Helped | Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024 · 64 citations) |
| Use normal-conditioned ControlNet | Image-guided texture transfer · shape-texture consistency | Helped | TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 2024 · 40 citations) | |
| increase the shell count from 1 to 2 | SHHQ, 128² resolution · FID | 40.3 -> 25.31 | Helped | Gaussian Shell Maps for Efficient 3D Human Generation (CVPR 2024 · 38 citations) |
| add multi-view inversion rather than relying on single-view inversion | Ablation test set · LPIPS | 0.1443 -> 0.0997 | Helped | Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image (CVPR 2024 · 14 citations) |
| Increase simultaneously relit frames from 1 to 64 | Objaverse standard assets · PSNR | 28.39 -> 31.34 | Helped | Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · 5 citations) |
| Add back-projected image measurements | Relighting dataset · PSNR-A | 24.780 -> 25.074 | Helped | ARM: Appearance Reconstruction Model for Relightable 3D Generation (CVPR 2025 · 3 citations) |
| Add RGB image features to GeoNet | Template deformation · CD | 1.150 -> 1.070 | Helped | Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · 2 citations) |
| Add recursive initialization to barycenter optimization | Shape interpolation ablation · FID | 12.52 -> 4.01 | Helped | Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models (NeurIPS 2025 · 1 citation) |
| add contextual embeddings to plane detection | DeepCAD reconstruction · Median CD | 0.39 -> 0.20 | Helped | MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 6 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Objaverse · 3 of 6 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 18 papers; from OpenAlex and the papers' affiliations).
- Hong Kong University of Science and Technology · 2 papers
- Tencent · 2 papers
- ShanghaiTech University · 2 papers
Use it
Download BibTeX of 27 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Gaussian and implicit head avatars (115 papers)
- Full-body avatar reconstruction (78 papers)
- Clothed human modeling (60 papers)
Elsewhere in the topic
- Neural implicit surface reconstruction (131 papers)
- Textured mesh generation (111 papers)
- Primitive-based shape abstraction (99 papers)
- Single-view 3D reconstruction (96 papers)
- Face reflectance and relightable rendering (85 papers)
- 3D morphable face model regression (80 papers)
- Articulated and non-rigid shape learning (75 papers)
- 3D shape generative modeling (74 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).