arXiv Computer Vision
AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
2d ago
Scene-Consistent Illumination Transfer for Inserted Advertising Graphics
arXiv:2609.37951v1 Announce Type: new Abstract: Replacing a visible advertisement in a broadcast frame is geometrically straightforward but photometrically delicate. A pasted graphic can have the cor...
Hugging Face Trending Papers
Aug 17
TransAnyText: Translating Arbitrary Text in E-commerce Images via Structured Visual Generation
Cross-border e-commerce image translation is essential for global retail, where product images, banners, and detail pages need to be produced in different languages. Existing methods struggle to achieve accurate translation, faithful visual identity preservation, and easy-to-edit outputs, simultaneously.
arXiv AI
Jun 10
Improving Text-Instance Alignment Of Foreground Conditioned Out-Painting Via Customized Concept Embedding
arXiv:2606. 10892v1 Announce Type: cross Abstract: To showcase products, merchants often incur substantial costs creating high-quality display images.
arXiv Machine Learning
Jun 30
HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers
arXiv:2606. 29095v1 Announce Type: cross Abstract: Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short clips and applied to long-horizon videos through chunked sliding-window inference, often causing temporal discontinuities at chunk boundaries.
arXiv Computer Vision
Sep 7
SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset
The paper introduces SEAL, a plug‑and‑play module that enhances single‑image sticker personalization in diffusion models by adding a semantic‑guided spatial attention loss, a split‑merge token strategy, and structure‑aware layer restriction. SEAL integrates without altering the U‑Net backbone and addresses overfitting issues such as visual entanglement and structural rigidity. Alongside SEAL, the authors release StickerBench, a large sticker dataset with six attribute tags to enable systematic evaluation of identity preservation and contextual controllability.
arXiv AI
Jun 2
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
arXiv:2603. 00133v2 Announce Type: replace-cross Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement.