Research map / Image generation / Editing and style transfer
GIRAFFE HD: A High-Resolution 3D-Aware Generative Model
Yang Xue, Yuheng Li, Krishna Kumar Singh, Yong Jae Lee
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 |
|---|---|---|---|
| replace the low-capacity renderer with a style-based renderer and generate foreground/background separately | GIRAFFE HD · CompCar 512² | FID: 40.81 -> 8.36 | Improved |
| replace the low-capacity renderer with a style-based renderer and generate foreground/background separately | GIRAFFE HD · FFHQ 1024² | FID: 70.08 -> 10.13 | Improved |
| use GIRAFFE HD instead of GIRAFFE | GIRAFFE · FFHQ 256² | MBS: 99.15 -> 15.02 | Improved |
| use GIRAFFE HD instead of GIRAFFE | GIRAFFE · CompCar 256² | MBS: 88.89 -> 22.88 | Improved |
| add position sharing (ablation) | GIRAFFE HD · CompCar 256² | FID: 10.89 -> 7.22 | Improved |
| add environment sharing (ablation) | GIRAFFE HD · CompCar 256² | FID: 11.55 -> 7.22 | Improved |
| replace separate foreground/background style renderers with a single style-based renderer (ablation) | GIRAFFE HD · image generation | foreground-background disentanglement | Hurt |
| remove bounding box containment loss (ablation) | GIRAFFE HD · FFHQ 64² after 4000 training iterations | foreground-background disentanglement | Hurt |
| remove foreground coverage loss (ablation) | GIRAFFE HD · FFHQ 64² after 4000 training iterations | foreground-background disentanglement | Hurt |
Closest papers by meaning
- Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes (NeurIPS 2024 · similarity 0.84)
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis (ICML 2025 · similarity 0.84)
- WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space (ICLR 2024 · similarity 0.84)
- DiffuseHigh: Training-Free Progressive High-Resolution Image Synthesis Through Structure Guidance (AAAI 2025 · similarity 0.83)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · similarity 0.83)
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (CVPR 2025 · similarity 0.83)
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.
