← Back to all news
arXiv Computer Vision By Luo Li, Chongchong Huang, Jun Jia, Qiang Gao, Xinlong Liu, Gui Yang, Liang Cao

Structured-Prior-Guided Diffusion Inpainting with Physical Consistency for Traffic Sign Augmentation

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Aug 13

Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment

arXiv:2608. 11537v1 Announce Type: cross Abstract: Generative semantic segmentation exposes structured predictions as images, but direct color decoding is susceptible to color drift and boundary mixing, whereas latent-feature decoders that predict a separate output distribution may relegate the rendered image to an intermediate visualization.

By Weize Cai, Yongqi Dong, Zhida Shao, Zixin Fu
diffusioncomputer-visionfine-tuningsafety
More like this →
arXiv Computer Vision
Sep 2

Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model

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.

By Zhenhuan Wang, Fengyi Yuan
diffusion
More like this →
arXiv Computer Vision
6d ago

The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation

The paper investigates how knowledge distillation from event cameras to RGB images can alter the inductive biases of convolutional neural networks. By transferring learning from the event domain, the authors find that models gain color invariance, a shape bias, and improved robustness to high‑frequency noise, largely due to reduced reliance on texture and increased emphasis on edge‑based object shape. These changes are evidenced by early‑layer processing differences and a spectral trade‑off between robustness to missing high‑frequency content and vulnerability to its contamination or geometric disruption.

By Soshun Kihara, Shunsuke Yasuki, Masato Taki
efficiencybenchmarkssafety
More like this →