Research map / 3D vision / Face and shape
AG3D: Learning to Generate 3D Avatars from 2D Image Collections
Zijian Dong, Xu Chen, Jinlong Yang, Michael J. Black, Otmar Hilliges, Andreas Geiger
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add normal discriminators (adversarial loss on predicted 2D normal maps) (ablation) | AG3D · DeepFashion | FID_normal: 32.17 -> 20.38 | Improved |
| add normal discriminators (ablation) | AG3D · DeepFashion | FID_face: 14.35 -> 14.79 | Mixed |
| add face discriminators (ablation) | AG3D · DeepFashion | FID_face: 20.88 -> 14.79 | Improved |
| add face discriminators (ablation) | AG3D · DeepFashion | FID: 11.71 -> 10.93 | Improved |
| use Fast-SNARF-based deformer instead of SMPL nearest-neighbor deformer (ablation) | AG3D · loose clothing (qualitative) | deformation artifacts | Improved |
| use holistic monolithic generator instead of compositional part-based generator (vs EVA3D) | AG3D · DeepFashion | FID: 20.45 -> 10.93 | Improved |
| use holistic generator with SMPL-guided rendering instead of EVA3D | AG3D · 512x512 rendering | FPS: 3 -> 9.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- EVA3D — EVA3D: Compositional 3D Human Generation from 2D Image Collections (ICLR 2023) · better on 2 of 2 shared results
- StyleSDF — StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- gDNA: Towards Generative Detailed Neural Avatars (CVPR 2022 · similarity 0.92)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024 · similarity 0.91)
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.91)
- Learning to Dress 3D People in Generative Clothing (CVPR 2020 · similarity 0.91)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.90)
- Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models (NeurIPS 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
