CORTEXA
← Browse
arxivcs.CV2026-07-22

Importance-Aware OBS Pruning for Diffusion Models

Ba-Thinh Lam, Srijan Das, Hieu Le

We propose importance-aware pruning for diffusion models, a training-free framework that prioritizes preserving parameters critical to semantically salient image regions. To do so, we incorporate spatial importance maps -- derived from conditioning signals or model attention -- into the pruning objective. This produces parameter rankings aligned with perceptual relevance rather than uniform reconstruction error. On MS-COCO dataset, our proposed approach consistently retains subject fidelity and structural correctness at high compression ratios where conventional pruning causes visible degradation. These results demonstrate that content-aware objectives are key to perceptually faithful compression of generative models.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-24

TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution

Sicheng Gao, Zhuyun Zhou, Yixuan Liu, Tong Shen, Zongwei Wu, Radu Timofte

Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due to the quadratic computational cost of processing dense spatio-temporal token sequences. Existing efficiency-oriented methods ris…

View free PDFSource page
arxivcs.CV2026-07-23

Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model

Shuaiwei Wang, Shi Li, Jieting Xu, Yuchi Huo, Qi Wang, Wenting Zheng, et al.

Numerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture maps and focus on natural images. An efficient and generalizable texture super-resolution model can revitalize a large corpus of aging yet valuable assets across i…

View free PDFSource page
arxivcs.CVcs.LG2026-07-11

GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization

Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, Kah Ong Michael Goh, S. M. Hasan Mahmud, Md Mahfuzur Rahman

Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality. Existing deep learning-based low-dose CT (LDCT) reconstruction methods are typically…

View free PDFSource page
arxivcs.CV2026-06-27

SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending

Haoran Bai, Xiaoxu Chen, Xiaoyu Liu, Zongsheng Yue, Sibin Deng, Wangmeng Zuo, et al.

While diffusion models excel in video restoration, their reliance on extensive iterative steps limits efficiency. Conversely, aggressive single-step distillation often compromises fine texture recovery. To achieve an optimal balance, we present SATB-VR, a few-step paradigm that j…

View free PDFSource page