The Visual Computer
Издатель: Springer Nature · ISSN 0178-2789,1432-2315 · 1097 статей
- Quality-aware visual-inertial GPS/SINS coarse alignment in a transverse frame for robust polar navigation
- PGSR-DR: high-fidelity reflective surface reconstruction with planar-based Gaussians and deferred rendering
- PolarNet: enhanced polar-coordinate lane detection via feature fusion and geometry-aware adaptive weighting
- Enhanced multi-scale feature fusion for accurate steel surface defect detection
- SplatSurf: bridging Gaussian splatting and surface geometry via triangle-soup
- Efficient multi-scale feature fusion for lightweight remote sensing image recognition
- LP-Swin: enhancing MRI brain tumor segmentation through Laplacian pyramid-guided swin transformer
- Competitive fusion in multimodal networks for enhanced salient object detection
- FEAO: a feature-enhanced network for real-time ambient occlusion
- Low-resource video-conditioned music generation via reliability-aware visual–text–audio fusion
- VCR-ShipFormer: visibility-conditioned transformer learning for robust vessel detection in degraded inland waterway scenes
- PSR-Net: process-state consistency verification for industrial image tampering detection and localization
- TDNet: degradation-aware comprehensive task decomposition for joint rain and haze removal
- Generalizable 3D Gaussian splatting with cross-view attention and frequency-aware bidirectional coordination
- Enhancing UAV small-object detection via spatial–frequency synergy and polarity-aware attention
- Attention-driven feedback for adaptive semantic augmentation in fine-grained visual classification
- Rectangling stitched images via unsupervised warping
- VGRR-Net: a reproducible visual computing framework for visibility-gap-driven collaborative 3D perception in low-altitude flying-car traffic
- Hybrid token learning with bidirectional attention for few-shot semantic segmentation
- Sami-Font: structure and style-aware multi-scale infusion for one-shot multilingual typeface generation
- Enhancing low-light images via text-guided multimodal learning
-
DSR-Net: decoder supervision and reconstruction for hybrid 3D medical segmentation
Abstract Hybrid CNN–Transformer networks have become effective architectures for 3D medical image segmentation by combining convolutional locality with attention-based context modeling. Most architectural improvements in this direction...
- Simple labels, rich supervision: a self-adaptive label expansion based weakly supervised camouflaged object detection
- HAFMat: Hybrid priors guided adaptive fusion for single-image human material estimation
- Portraitagent: verified multi-agent diffusion editing for identity-preserving portrait manipulation
- Uncertainty-aware multi-view post-aggregation for point cloud quality assessment
- Multi-scale feature fusion attention network: enhancing edge super-resolution of variable-resolution optical satellite images
- Vision-language models meet hand gesture recognition: towards multimodal and intelligent human-computer interaction
- AppleDet: lightweight and robust apple detection in natural orchard environments via reparameterized and state space visual modeling
- Baseball pitching motion reconstruction from single-view videos