4 papers · 1 filter
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
Zhaoyang Li, Zhichao You, Tianrui Li
Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, y…
Degradation-Aware Adaptive Context Gating for Unified Image Restoration
Lei He, Jielei Chu, Fengmao Lv +4
Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Ga…
Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation
Qiyang Yu, Yu Fang, Tianrui Li +5
Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts dire…
Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting
Qiyang Yu, Yu Fang, Tianrui Li +4
Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing m…