Cvpr 2026 Anchorsplat

AnchorSplat

CVPR 2026

Authors: Shubhankar Borse, Farzad Farhadzadeh, Munawar Hayat, Fatih Porikli.

MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention.

Project Page https://masatate.github.io/HanDyVQA-project-page/ ArXiv https://arxiv.org/abs/2512.00885.

Authors: Matteo Ballegeer, Dries F. Benoit Paper: https://arxiv.org/abs/2602.24084 Google Scholar: ...

Rameen Abdal, James Burgess, Sergey Tulyakov, Kuan-Chieh Wang Snap Research , Stanford University ...

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement.

Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios Zhipeng Sui, ...

UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair Project Page: ...

View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification.

Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset.

Omni-Attribute encodes a high-fidelity, attribute-specific image representation, that enables coherent synthesis of the ...