TL;DR
The Visual-Spatial Latent Graph Network (VSLG-Net), a parameter-compact transformer-based framework with dual-branch for local and global context perception in attention mechanisms, is proposed, which achieves competitive performance on the outdoor YFCC100M benchmark and remains competitive on the indoor SUN3D benchmark, compared with state-of-the-art methods.
Learning reliable two-view correspondences is essential for geometric computer vision applications. Existing graph-based pruning methods typically aggregate information unidirectionally, capturing only whether a correspondence receives neighborhood support while ignoring its structural contribution during aggregation....
This work presents VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis, and introduces robust geometry conditioning, combining training-time regularization with inference-time guidance for improved robustness.
A Graph-driven Contextual Synergy Network (GCS3D), which is designed to systematically enhance point representations across both semantic and geometric dimensions, and introduces a Graph-guided Geometric Consistency Interaction module for contextual correlation modeling.
A Prior-Guided Part Aggregator (PGA) is designed, which leverages the foreground prior provided by foundation models to guide discriminative part discovery, enhancing target region responses while suppressing background interference, and a Topology-Informed Semantic Graph Convolutional Network (TIS-GCN) is designed to...
Recent advances in single image super-resolution (SISR) have leveraged convolutional neural networks (CNNs) and vision transformers to model pixel-level statistics, often relying on increasingly complex architectures to capture spatial correlations. However, these approaches generally overlook a fundamental distinction...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
