activity
20222026
most citedLearning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement

20 citations · 44 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2026

CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction

Zhirui Gao, Renjiao Yi, Yunfan Ye +4

Recovering editable 3D parametric curves from 2D images is a fundamental challenge in computer graphics, bridging pixel-based perception and vector-based CAD modeling. Existing NeR…

cs.CV2026

Video-HOCA: A Diagnostic Benchmark for Physical Anomaly Reasoning in Video-LLMs

Chang Liu, Yunfan Ye, Qingyang Zhou +5

We introduce Video-HOCA, a diagnostic benchmark for physical anomaly reasoning in videos. Video-HOCA uses an Ontological-Causal taxonomy to distinguish violations of an entity's ow…

cs.CV2025

HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly

Chang Liu, Yunfan Ye, Fan Zhang +3

Numerous synthesized videos from generative models, especially human-centric ones that simulate realistic human actions, pose significant threats to human information security and…

cs.CV2024

ROICtrl: Boosting Instance Control for Visual Generation

Yuchao Gu, Yipin Zhou, Yunfan Ye +5

Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to s…

cs.CV2024★ 4 cited

DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection

Yunfan Ye, Kai Xu, Yuhang Huang +2

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent…

cs.CV2023★ 19 cited

Delving into Crispness: Guided Label Refinement for Crisp Edge Detection

Yunfan Ye, Renjiao Yi, Zhirui Gao +2

Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled…