← Search

Haoxiang Hu

4 accepted papers

2026

Diagram2Structure: Unlocking LLMs' Diagram Comprehension through DiagramDiff, a Framework for Structuring Offline Diagrams

CVPR 2026

Diagrams are widely used in daily life. However, offline diagrams typically exist in the form of images, lacking structured data representation, which significantly limits their reusability and editability. Current research mainly focuses on supporting basic query tasks for online diagrams and does

Cited by 0SourceScholar
2026

SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMs

CVPR 2026

Transforming sparse, partial pixel sketches from diverse media into complete, editable vector drawings is essential yet underexplored in digital creation. Prior methods either generate from scratch or inpaint local gaps without predicting global structure, leading to coarse contours and limited deta

Cited by 0SourceScholar
2024

SceneDiff: Generative Scene-Level Image Retrieval with Text and Sketch Using Diffusion Models

IJCAI 2024poster

Jointly using text and sketch for scene-level image retrieval utilizes the complementary between text and sketch to describe the fine-grained scene content and retrieve the target image, which plays a pivotal role in accurate image retrieval. Existing methods directly fuse the features of sketch and…

Cited by 0SourcePDFScholar
2024

SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation

AAAI 2024technical

Online handwriting recognition is pivotal in domains like note-taking, education, healthcare, and office tasks. Existing diagram recognition algorithms mainly rely on the temporal information of strokes, resulting in a decline in recognition performance when dealing with notes that have been modifie…

Cited by 2SourcePDFScholar