The Visual Computer
Publisher: Springer Nature · ISSN 0178-2789,1432-2315 · 1097 articles
- Plkdcn: lightweight single-image super-resolution via partial large-kernel depthwise convolution
- Msagnet: a multi-scale attention graph neural network for self-collision-aware garment dynamics simulation
- Supervision-assisted token reconstruction for data-efficient retinal disease classification
- Monocular-depth-guided open-set surface defect segmentation via cross-modal visual representation and distribution-structured anomaly modeling
- CL-HPE: enhancing human pose estimation via lightweight structural attention mechanisms
- Adaptive spherical-harmonic allocation and saliency pruning for memory-efficient 3D Gaussian splatting
- Mamba-UIQA: physics-guided state-space modeling for no-reference underwater image quality assessment
- Semantic bridge-guided training-free open-vocabulary segmentation for fashion visual understanding
- DCS-Font: dynamic feature enhancement for few-shot font generation
- LiteBDS-ViT: hardware-friendly block-diagonal shift projections for efficient low-precision vision transformers
- Generative adversarial imitation learning with sequential trajectory inpainting for UAV navigation in dynamic environments
- Enhancing video anomaly detection through dual-path reconstruction and diverse pseudo-anomaly generation
- Dynamic spectral-causal risk minimization for robust cross-domain visual recognition
- DPSAM2: memory-guided dual-path adaptation of SAM2 for boundary-aware low-contrast segmentation
- AHD-YOLO: An efficient front-end perception framework for vision-based drowning-risk monitoring in complex water-surface environments
- Hybrid representation and adaptive multi-feature fusion for monocular 6D pose estimation in industrial assembly
- Diamojism: semantic-perceptual tile selection for large-format emoji mosaic rendering
- MoR-ST: content-adaptive recursive computation for efficient vision transformers
- Enhancing 3D shape recognition with multi-view relational transformer networks
- AA3D: attacking embodied object navigation with viewpoint-robust 3D adversarial examples
- Data-free neural mesh inpainting: preserving topology and geometry
-
Quality evaluation of automatically estimated BRDF models
Abstract The Bidirectional Reflectance Distribution Function (BRDF) is widely used in computer graphics to model material appearance based on light and view directions, though it neglects other dependencies, such as spatial. While...
- Boundary-guided frequency fusion for facial attribute editing forgery detection and localization
- MS-SLAM: Memory-augmented 3D Gaussian splatting SLAM for efficient robotic applications
- Ow-Mamba: modality-adaptive 3D brain tumor segmentation for single- and partial-modality MRI
- IM-Font: IDS-guided multi-stage diffusion for one-shot Chinese font generation
- Prior-calibrated spatial-frequency Retinex decomposition for unsupervised low-light image enhancement
- D2M-Net: decoupled dual matching for few-shot 3D point-cloud semantic segmentation
- Frequency-aware dual-stream learning for balanced realism and fidelity in electron microscopy imaging
- MSPD-net: structural–appearance prototype decoupling for weakly supervised semantic segmentation