Research map / Image generation / Text-to-image diffusion
Pinco: Position-induced Consistent Adapter for Diffusion Transformer in Foreground-conditioned Inpainting
Guangben Lu, Yuzhen Du, Yizhe Tang, Zhimin Sun, Ran Yi, Yifan Qi, Tianyi Wang, Lizhuang Ma, Fangyuan Zou
This paper tried a common change: Add positional encoding
add Shared Positional Embedding Anchor (RoPE on key) · ablation eval · OER (SAM2.1): 290.44% -> 11.51% Improved
What 646 accepted papers report for this change
- 525 improved
- 58 no clear effect
- 7 mixed
- 56 hurt
- Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts ICML 2026 · add positional encodings to features (d=13 -> d=21) · Block-structured, N=4096 · speedupImproved
- Mesh Based Simulations with Spatial and Temporal awareness ICML 2026 · use learned positional embedding, learnable relative bias or weighted adjacency instead of RoPE · Aneurysm · RMSEHurt
- Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning ICML 2026 · add sinusoidal positional encoding to the pruner · Robomimic Tool Hang · success rate (%): 28 -> 54Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 |
|---|---|---|---|
| inject subject features in self-attention instead of cross-attention (ablation) | HY-Pinco · ablation eval | OER (SAM2.1): 14.55% -> 11.51% | Improved |
| inject subject features in self-attention instead of cross-attention (ablation) | HY-Pinco · ablation eval | FID: 85.61 -> 84.25 | Improved |
| inject subject features in self-attention instead of cross-attention (ablation) | HY-Pinco · ablation eval | VQAScore: 0.892 -> 0.901 | Improved |
| inject subject features in self-attention instead of cross-attention (ablation) | HY-Pinco · ablation eval | FV2Score: 3.51% -> 3.16% | Improved |
| add Decoupled Image Feature Extractor over VAE-only (ablation) | HY-Pinco · ablation eval | OER (SAM2.1): 36.11% -> 11.51% | Improved |
| add Decoupled Image Feature Extractor over VAE-only (ablation) | HY-Pinco · ablation eval | OER (BiRefNet): 14.58% -> 10.00% | Improved |
| add Shared Positional Embedding Anchor (RoPE on key) (ablation) | HY-Pinco · ablation eval | OER (SAM2.1): 290.44% -> 11.51% | Improved |
| add Shared Positional Embedding Anchor (RoPE on key) (ablation) | HY-Pinco · ablation eval | OER (BiRefNet): 68.64% -> 10.00% | Improved |
| add Shared Positional Embedding Anchor (RoPE on key) (ablation) | HY-Pinco · ablation eval | GPT4o rationality: 4.820 -> 4.790 | Hurt |
| add DIFE over VAE-only (ablation) | HY-Pinco · ablation eval | TPR: 9.48% -> 11.37% | Hurt |
| use Pinco adapter instead of ControlNet on Flux (ablation) | HY-Pinco · Flux.1 comparison | OER (SAM2.1): 28.11% -> 7.87% | Improved |
| use Pinco adapter instead of ControlNet on Hunyuan-DiT (ablation) | HY-Pinco · Hunyuan-DiT comparison | FV2Score: 5.00% -> 3.16% | Improved |
Closest papers by meaning
- ATA: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting (CVPR 2025 · similarity 0.90)
- CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility (AAAI 2025 · similarity 0.86)
- TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting (CVPR 2025 · similarity 0.85)
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (AAAI 2024 · similarity 0.85)
- HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025 · similarity 0.85)
- DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework (AAAI 2025 · similarity 0.85)
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.
