Skip to content
Preprint

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

Sep 2026 · 0 citations · 50 references
Computer Science

TL;DR

This work proposes a structured-prior-guided diffusion inpainting framework with physical consistency that beats seven representative competitors on every metric of reconstruction fidelity, physical consistency and semantic controllability in traffic sign detection.

Abstract

Traffic sign detection faces a long-tailed data distribution. Many rare signs matter as much as common ones from a regulatory standpoint, yet they have very few samples. Generative data augmentation is one way out. General-purpose inpainting models, however, distort digits, deform geometry and perspective, and shift colours when applied directly to sign regions. We trace this to a single gap: the conditioning signal is too abstract for the physical composition of a sign. We propose a structured-prior-guided diffusion inpainting framework with physical consistency. It injects the semantic, appearance and geometric priors of a sign through three orthogonal pathways: a JSON-formatted text prompt, a front-view vector template rendered with measured dominant colours (via IP-Adapter), and an affine-aligned vector template (via ControlNet). Two physical consistency losses constrain colour with a CIELAB chromaticity $L_1$ term and edge structure with a Sobel gradient term. We train by self-supervised reconstruction on a large set of images collected in-house at AMAP, then evaluate zero-shot on the public TT100K-2021 dataset, a different source. Our method uses a Stable Diffusion 1.5 backbone of about 1.4B parameters. It beats seven representative competitors on every metric of reconstruction fidelity, physical consistency and semantic controllability. Its OCR exact-match rate reaches 91.1\%, against 44.2\% for the 12B industrial model FLUX.1 Fill [dev], and it needs only $1/14$ of that model's inference time. Leave-one-out ablations confirm that each of the three prior pathways and both loss terms contribute on their own. In downstream detection, the synthetic data raises the group-pooled AP50 of rare classes by $1.23\times$ to $7.40\times$ over a real-data-only baseline. Code and pre-trained models are available at https://github.com/52hz-whale/TrafficSignInpaint.

View source

Similar papers

Open access Oct 2026

Focus-and-Disperse: A Fine-to-Broad Context Aggregation for Image Inpainting

The Focus-and-Disperse Inpainting (FDInpaint), a fine-to-broad context aggregation network that follows a focus-and-disperse paradigm that achieves superior restoration accuracy and visual quality compared with state-of-the-art inpainting methods is proposed.

Jia Qin, Yue Lv, Shuang-Jiao Zhai et al. · 0 citations
Preprint Oct 2026

DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization

Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line of work has exploited these strong 3D priors for training-free stylization, transferring visual attributes from a reference image onto a generated 3D asset. However, exi...

Tao Wu, Alex Gomez-Villa, Sen-Mao Li et al. · 0 citations
#artificial intelligence Preprint Oct 2026

AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation

Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrained model. We study this tension in a 5.01B-parameter text-to-video diffusion transformer. ACROSSVAM2.0 combines a confidence-weighted track...

Nan Wu, Yee-Hung Hong · 0 citations
Sep 2026

DMA2: Pixel-space Distribution Matching with Adversarial and Anchor Losses

Distribution matching distillation (DMD) provides a general framework for few-step diffusion generation, but its modern text-to-image instantiations have been developed primarily around latent diffusion. It therefore overlooks key properties and design opportunities of native RGB. We revisit two DMD interfaces for pixe...

Xin Lin, Zhi-Fei Zhang, Yu-Qian Zhou et al. · 0 citations
Open access Oct 2026

Structure-Guided Texture Enhancement and Multi-Scale Feature Fusion for Progressive Mural Inpainting

Progressive mural inpainting requires structural guidance to reconstruct missing textures while maintaining color consistency. Existing methods only introduce line constraints at the input stage, resulting in distorted structures and color mismatch for severely damaged murals. This paper proposes SGMA-MuralNet, a two-s...

Jiang-Hao Li, Yu Fang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.