Jiajun Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiajun Liu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Jing Li
College of Science & Technology, Ningbo University, Ningbo 315300, China
2 shared publications - Qiang Fu
College of Science & Technology, Ningbo University, Ningbo 315300, China
2 shared publications - Zhiping Wu
College of Science and Technology, Ningbo University, Ningbo 315300, China
2 shared publications
Latest Publications
- Open Access
- 17 April 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (6)
ASCR-DETR: Enhanced industrial fabric defect detection with Adaptive Spatial Geometry Convolution and Context-Guided Spatial Reconstruction
- 17 April 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (6)
Open AccessASCR-DETR: Enhanced industrial fabric defect detection with Adaptive Spatial Geometry Convolution and Context-Guided Spatial Reconstruction
- Open Access
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1208
Knit-Edit: A Unified Multi-Task Editing Framework for Knitted Garments
Generative Artificial Intelligence has shown immense potential in industrial design. However, applying Diffusion Transformers to precision manufacturing faces a critical bottleneck: the trade-off between flexible multi-task editing and high-fidelity texture preservation. Existing methods often suffer from “texture collapse” when merging multiple adapters, failing to maintain the intricate topological structures required for industrial standards. To address this, we present Knit-Edit, a unified framework for high-precision knitted garment editing. Our core contribution is EditLoRI, a novel task decoupling mechanism utilizing orthogonal Low-Rank Adaptation. By projecting task-specific gradients into orthogonal subspaces, EditLoRI enables the interference-free composition of multiple editing capabilities within a single lightweight model. Furthermore, we introduce a structure-preserving spatial guidance strategy using Bounding Boxes to resolve the localization ambiguity of text prompts. Validated on our constructed KnitEdit dataset, the proposed method significantly outperforms state-of-the-art baselines in controllability and structural fidelity, offering a robust solution for intelligent generative manufacturing.
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1208
Open AccessKnit-Edit: A Unified Multi-Task Editing Framework for Knitted Garments
Generative Artificial Intelligence has shown immense potential in industrial design. However, applying Diffusion Transformers to precision manufacturing faces a critical bottleneck: the trade-off between flexible multi-task editing and high-fidelity texture preservation. Existing methods often suffer from “texture collapse” when merging multiple adapters, failing to maintain the intricate topological structures required for industrial standards. To address this, we present Knit-Edit, a unified framework for high-precision knitted garment editing. Our core contribution is EditLoRI, a novel task decoupling mechanism utilizing orthogonal Low-Rank Adaptation. By projecting task-specific gradients into orthogonal subspaces, EditLoRI enables the interference-free composition of multiple editing capabilities within a single lightweight model. Furthermore, we introduce a structure-preserving spatial guidance strategy using Bounding Boxes to resolve the localization ambiguity of text prompts. Validated on our constructed KnitEdit dataset, the proposed method significantly outperforms state-of-the-art baselines in controllability and structural fidelity, offering a robust solution for intelligent generative manufacturing.