Research map / 3D vision / Face and shape
REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
Hankyeol Lee, Wooyeol Baek, Seongdo Kim, Jongyoo Kim
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 |
|---|---|---|---|
| apply REVIVE 3D refinement on Hunyuan3D-2.1 | Hunyuan3D-2.1 · Flat-image test set | Compactness: 0.1408 -> 0.2179 | Improved |
| apply REVIVE 3D refinement on Hunyuan3D-2.1 | Hunyuan3D-2.1 · Flat-image test set | Normal Anisotropy: 0.1347 -> 0.0767 | Improved |
| apply REVIVE 3D refinement on Hunyuan3D-2.1 | Hunyuan3D-2.1 · Flat-image test set | Uni3D: 0.2759 -> 0.3043 | Improved |
| apply REVIVE 3D refinement on Direct3D | Direct3D · Flat-image test set | Compactness: 0.2012 -> 0.2178 | Improved |
| apply REVIVE 3D refinement on Direct3D | Direct3D · Flat-image test set | ULIP: 0.1315 -> 0.1375 | Improved |
| lower initial noise level from 0.8 to 0.6 (ablation) | REVIVE 3D · Art3D | Compactness: 0.2691 -> 0.4296 | Mixed |
| lower initial noise level from 0.8 to 0.6 (ablation) | REVIVE 3D · Art3D | Uni3D: 0.3382 -> 0.3043 | Hurt |
| raise initial noise level from 0.8 to 1.0 (ablation) | REVIVE 3D · Art3D | Compactness: 0.2691 -> 0.1501 | Hurt |
| raise initial noise level from 0.8 to 1.0 (ablation) | REVIVE 3D · Art3D | Uni3D: 0.3382 -> 0.3003 | Hurt |
| reduce inflation strength from 1.5 to 0.1 (ablation) | REVIVE 3D · Art3D | Compactness: 0.2691 -> 0.1172 | Hurt |
| reduce inflation strength from 1.5 to 0.1 (ablation) | REVIVE 3D · Art3D | Normal Anisotropy: 0.0610 -> 0.2539 | Hurt |
| raise inflation strength from 1.5 to 6.0 (ablation) | REVIVE 3D · Art3D | Compactness: 0.2691 -> 0.2682 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Direct3D — DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data (CVPR 2024) · better on 4 of 4 shared results
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
- 3D-ReGen: A Unified 3D Geometry Regeneration Framework (ECCV 2026 · similarity 0.88)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · similarity 0.87)
- Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior (ICCV 2023 · similarity 0.87)
- Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention (NeurIPS 2025 · similarity 0.87)
- Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion (CVPR 2025 · similarity 0.87)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.86)
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.
