Score: 1

C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

Published: August 30, 2025 | arXiv ID: 2509.00578v3

By: Abdellah Zakaria Sellam , Ilyes Benaissa , Salah Eddine Bekhouche and more

Potential Business Impact:

Helps computers see tiny damage on cars.

Business Areas:
Image Recognition Data and Analytics, Software

Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through conditional denoising diffusion, its performance remains limited by local feature conditioning in context-dependent scenarios. We address this fundamental limitation by introducing Context-Aware Fusion (CAF), which leverages cross-attention mechanisms to integrate global scene context with local proposal features directly. The global context is generated using a separate dedicated encoder that captures comprehensive environmental information, enabling each object proposal to attend to scene-level understanding. Our framework significantly enhances the generative detection paradigm by enabling each object proposal to attend to comprehensive environmental information. Experimental results demonstrate an improvement over state-of-the-art models on the CarDD benchmark, establishing new performance benchmarks for context-aware object detection in fine-grained domains

Page Count
44 pages

Category
Computer Science:
CV and Pattern Recognition