The paper introduces IS‑Diff, a training‑free diffusion‑based inpainting method that improves semantic consistency by using initial seeds sampled from unmasked regions. It incorporates a dynamic selective refinement mechanism to adjust the initialization strength during intermediate latent stages. Experiments on CelebA‑HQ, ImageNet, and Places2 show that IS‑Diff outperforms state‑of‑the‑art methods across standard and large‑mask inpainting tasks.
arXiv:2603.23463v2 Announce Type: replace-cross Abstract: Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text...
arXiv:2607. 10580v1 Announce Type: cross Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising.
arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.
The paper introduces D3S2, a diffusion‑guided dataset distillation framework tailored for semantic segmentation. It tackles long‑tailed class imbalance, pixel‑wise alignment, and high computational cost by first selecting class‑balanced masks and then synthesizing images with a pretrained diffusion model conditioned on those masks. Guided diffusion sampling further refines the data with segmentation‑consistency and class‑wise feature matching losses, achieving superior performance at a 1% compression rate on ADE20K and COCO‑Stuff.
EraseSAE introduces a surgical concept erasure method for text-to-video diffusion models, using sparse autoencoders to decompose activations into interpretable, monosemantic features. The framework employs a contrastive attribution mechanism to isolate concept-specific kernels and applies timestep-resolved masks during inference to remove target concepts while preserving unrelated content. Experiments show that EraseSAE achieves precise, robust concept removal with minimal quality loss, outperforming existing methods.
The paper demonstrates that a frozen generic text‑to‑image diffusion model can perform conditional inpainting across three natural‑image domains without any inpainting‑specific training or dataset adaptation. The proposed Step‑PI method augments known‑region projection with boundary‑interior latent feedback, persistent PI state, and a predefined four‑field release schedule, improving all evaluated metrics over baseline training‑free approaches. Experiments on CelebA‑HQ, AFHQ, and Places2 show consistent gains, with Step‑PI outperforming LanPaint and PILOT on all five macro metrics.
The paper introduces "overpainting," a localized, context-aware image editing technique that allows users to specify precise or loose editing regions via a trimap. The method adapts a pretrained diffusion model with joint attention and low‑rank adaptation, incorporating attention‑dropout to balance noise, source, and mask inputs. An automated pipeline generates training data by pairing images from language‑based editing models, curating them, and extracting trimaps, enabling the model to perform a wide range of editing tasks.
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and related metrics, it is increasingly unclear whether they reflect real progress in generative modeling.
arXiv:2607. 05319v1 Announce Type: cross Abstract: We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures.
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
arXiv:2609.23967v1 Announce Type: cross Abstract: Diffusion models are increasingly adapted from generation to conditional prediction, where a conditioning signal is combined with an evolving noisy r...
The paper introduces a structured‑prior‑guided diffusion inpainting framework that enhances traffic sign augmentation by incorporating semantic, appearance, and geometric priors through text prompts, vector templates, and ControlNet. It enforces physical consistency with colour and edge‑structure losses, achieving superior reconstruction fidelity and OCR accuracy compared to larger models. The synthetic data generated improves detection performance for rare traffic sign classes by up to 7.4× over a real‑data‑only baseline.