Cvpr 2026 Processmaker

ProcessMaker

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

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

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

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

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

CVPR 2026

Chart-FR1 Paper Presentation at

VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network.

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

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed ...

[

Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation》 In stroke-based ...

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

How much do video diffusion models know about the 4D world? By introducing a 4D VAE, we jointly estimate geometry and ...

[

TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classification.

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization (