A new 100k triplet dataset and in-context diffusion framework ICTone enable state-of-the-art tone style transfer by jointly conditioning on content and reference images with scorer-based reward learning.
Ic-custom: Diverse image customization via in-context learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
LCG introduces Sparse Relational Attention and Routing Consistency Constraint to produce consistent multi-image text-to-image sequences and reports better prompt alignment and character consistency than baselines on a new 600K-sequence synthetic dataset.
citing papers explorer
-
Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset
A new 100k triplet dataset and in-context diffusion framework ICTone enable state-of-the-art tone style transfer by jointly conditioning on content and reference images with scorer-based reward learning.
-
PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
-
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
-
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
LCG introduces Sparse Relational Attention and Routing Consistency Constraint to produce consistent multi-image text-to-image sequences and reports better prompt alignment and character consistency than baselines on a new 600K-sequence synthetic dataset.