Research map / 3D vision / 3D generation
Coupled Diffusion Sampling for Training-Free Multi-View Image Editing
Hadi Alzayer, Yunzhi Zhang, Chen Geng, Jia-Bin Huang, Jiajun Wu
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 |
|---|---|---|---|
| couple 2D editing model with multi-view diffusion (vs image-to-MV from one edited image) | multi-view diffusion · Spatial editing | PSNR: 12.84 -> 17.0 | Improved |
| couple 2D editing model with multi-view diffusion (vs per-image editing) | Magic Fixup · Spatial editing | MEt3r: 0.353 -> 0.335 | Improved |
| coupled sampling vs per-image editing | Magic Fixup · Spatial editing | LPIPS: 0.253 -> 0.421 | Hurt |
| coupled sampling vs score-averaging composition | Liu et al./Du et al. · Stylization | Subject consistency: 0.759/0.762 -> 0.807 | Improved |
| coupled sampling vs mesh-based methods | TEXTure/Hunyuan3D · Stylization | MEt3r: 0.391 (Hunyuan3D) vs 0.392 | No clear effect |
| coupled sampling vs composition baselines | Liu et al. · Relighting | PSNR: 23.2 -> 23.2 | No clear effect |
| coupled sampling vs per-image relighting | Neural Gaffer · Relighting | PSNR: 22.7 -> 23.2 | Improved |
| increase coupling strength lambda from small to moderate (ablation) | Coupled sampling · Spatial editing | reconstruction | Improved |
| increase coupling strength lambda too large (ablation) | Coupled sampling · Spatial editing | consistency | Hurt |
Closest papers by meaning
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.90)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor (CVPR 2024 · similarity 0.89)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.89)
- Posterior Distillation Sampling (CVPR 2024 · similarity 0.89)
- Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis (NeurIPS 2024 · similarity 0.89)
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.
