Cvpr 2026 Vimcan

VIMCAN

Title: Scene-Centric Unsupervised Video Panoptic Segmentation Authors: Christoph Reich*, Oliver Hahn*, Nikita Araslanov, ...

Hakyeong Kim, Ruicheng Wang, Chengtang Yao, Jiaolong Yang, Min H. Kim (

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

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

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

The 5-minute introduction video of IntrinsicWeather.

CVPR 2026：VEMamba

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

Hakyeong Kim, Ruicheng Wang, Chengtang Yao, Jiaolong Yang, Min H. Kim (

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

[

https://lucaria-academy.github.io/SynMotion/

Paper: https://arxiv.org/abs/2512.01390 Project Page: https://cmlab-korea.github.io/FRAMER/ Authors/Affiliations: [Seungho ...

[CVPR 2026] VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction

[

Joonki Min, Chaeyun Kim, Hyungwook Choi, Yejin Kim, Kihyun Kim, Yohan Jo, Joonseok Lee. Fine-Grained Multi-Image Object ...

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

This is the official 5-minute poster presentation video for