Research map / 3D vision / Face and shape
MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing
Xiaokun Sun, Zeyu Cai, Hao Tang, Ying Tai, Jian Yang, Zhenyu Zhang
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 |
|---|---|---|---|
| replace KV-fused cross-attention with Morphing Cross-Attention (ablation) | MorphAny3D · 3D morphing (50 pairs) | FID: 125.47 -> 112.18 | Improved |
| replace KV-fused cross-attention with MCA (ablation) | MorphAny3D · 3D morphing (50 pairs) | PPL: 3.82 -> 3.66 | Improved |
| add Temporal-Fused Self-Attention (ablation) | MorphAny3D (MCA) · 3D morphing (50 pairs) | PPL: 3.66 -> 2.87 | Improved |
| add Temporal-Fused Self-Attention (ablation) | MorphAny3D (MCA) · 3D morphing (50 pairs) | FID: 112.18 -> 113.22 | No clear effect |
| add orientation correction (ablation) | MorphAny3D (MCA+TFSA) · 3D morphing (50 pairs) | PPL: 2.87 -> 2.47 | Improved |
| add orientation correction (ablation) | MorphAny3D (MCA+TFSA) · 3D morphing (50 pairs) | FID: 113.22 -> 111.95 | Improved |
| apply both KV-fused CA and KV-fused SA (ablation) | Trellis morphing · 3D morphing (analysis) | FID | Hurt |
| MorphAny3D vs MorphFlow matching-based morphing | MorphAny3D · 3D morphing (50 pairs) | FID: 284.96 -> 111.95 | Improved |
| MorphAny3D vs 3DInterp | MorphAny3D · 3D morphing (50 pairs) | PPL: 2.55 -> 2.47 | Improved |
| MorphAny3D vs MorphFlow on smoothness | MorphAny3D · 3D morphing (50 pairs) | PPL: 2.41 -> 2.47 | Hurt |
Closest papers by meaning
- Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models (NeurIPS 2025 · similarity 0.88)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.87)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · similarity 0.86)
- Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization (CVPR 2025 · similarity 0.86)
- FLOWING: Implicit Neural Flows for Structure-Preserving Morphing (NeurIPS 2025 · similarity 0.86)
- 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.
