Cvpr 2026 Tape

TAPE

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

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

OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition (

We introduce our

In this video, we introduce a novel video object detection framework called D2FANet. D2FANet is the first framework to jointly ...

NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity.

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

[CVPR 2026] Hear What You See: Video-to-Audio Generation with Diffusion Transformer and STAR-DPO

More info: http://nikhilbehari.com/denali.

Title:MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene ...

AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors Paper: https://arxiv.org/abs/2604.07053.

Presentation video for our

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

[

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

CVPR 2026 TAR presentation

Video2Robo: 3DGS-based Synthetic Data from One Video Enables Scalable Robot Learning Project page: ...