SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models
원문 초록
While foundation models have revolutionised computer vision, their effectiveness for sketch understanding remains limited by the unique challenges of abstract, sparse visual inputs. Through systematic analysis, we uncover two fundamental limitations: Stable Diffusion (SD) struggles to extract meaningful features from abstract sketches (unlike its success with photos), and exhibits a pronounced frequency-domain bias that suppresses essential low-frequency components needed for sketch understanding. Rather than costly retraining, we address these limitations by strategically combining SD with CLIP, whose strong semantic understanding naturally compensates for SD's spatial-frequency biases. By dynamically injecting CLIP features into SD's denoising process and adaptively aggregating features across semantic levels, our method achieves state-of-the-art performance in sketch retrieval (+3.35%), recognition (+1.06%), segmentation (+29.42%), and correspondence learning (+21.22%), demonstrating the first truly universal sketch feature representation in the era of foundation models.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models
Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation
Energy-Based Transformers are Scalable Learners and Thinkers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.