Leveraging hallucinations to reduce manual prompt dependency in promptable segmentation

J Hu, J Lin, J Yan, S Gong - Advances in Neural Information …, 2025‏ - proceedings.neurips.cc
Promptable segmentation typically requires instance-specific manual prompts to guide the
segmentation of each desired object. To minimize such a need, task-generic promptable …

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

J Chen, J Yan, Y Fang, L Niu - Proceedings of the IEEE/CVF …, 2024‏ - openaccess.thecvf.com
Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes
given a few support images annotated with keypoints. Existing methods only rely on the …

Occlusion-Aware Seamless Segmentation

Y Cao, J Zhang, H Shi, K Peng, Y Zhang… - … on Computer Vision, 2024‏ - Springer
Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can
deepen the understanding of the scene, and domain adaptation can transfer across viewing …

PLUG: Revisiting Amodal Segmentation with Foundation Model and Hierarchical Focus

Z Liu, L Qiao, X Chu, T Jiang - arxiv preprint arxiv:2405.16094, 2024‏ - arxiv.org
Aiming to predict the complete shapes of partially occluded objects, amodal segmentation is
an important step towards visual intelligence. With crucial significance, practical prior …

Amodal instance segmentation with dual guidance from contextual and shape priors

J Zhan, Y Luo, C Guo, Y Wu, B Yang, J Wang… - Applied Soft Computing, 2025‏ - Elsevier
Human perception possesses the remarkable ability to mentally reconstruct the complete
structure of occluded objects, which has inspired researchers to pursue amodal instance …

Opnet: Deep Occlusion Perception Network with Boundary Awareness for Amodal Instance Segmentation

S Zhang, Z Xue, Y Jiang, H Wang - ICASSP 2024-2024 IEEE …, 2024‏ - ieeexplore.ieee.org
The Amodal Instance Segmentation (AIS) task aims to infer the visible and occluded regions
of an object instance. Existing AIS methods typically focus on directly predicting visible and …