Center for Advanced Intelligence Project

Five papers were accepted at CVPR 2026, a top conference on computer vision. For more details, please refer to the link below.

[Website] https://cvpr.thecvf.com/

• COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
  Yuchen Che (Institute of Science Tokyo)
  Jingtu Wu (Institute of Science Tokyo)
  Hao Zheng (RIKEN AIP)
  Asako Kanezaki (Institute of Science Tokyo / RIKEN AIP / Tohoku University).
• Direction-aware 3D Large Multimodal Models
  Quan Liu (Nanyang Technological University)
  Weihao Xuan (University of Tokyo / RIKEN AIP)
  Junjue Wang (University of Tokyo)
  Naoto Yokoya (University of Tokyo / RIKEN AIP)
  Ling Shao (University of the Chinese Academy of Sciences)
  Shijian Lu (Nanyang Technological University)
• GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing
  Aoran Xiao (RIKEN AIP)
  Shihao Cheng (Wuhan University)
  Yonghao Xu (Linköping University)
  Yexian Ren (Nanjing University of Information Science and Technology)
  Hongruixuan Chen (University of Tokyo)
  Naoto Yokoya (University of Tokyo / RIKEN AIP)
• MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation
  Chao Ning (University of Tokyo / RIKEN AIP)
  Minghe Shen (University College London)
  Naoto Yokoya (University of Tokyo / RIKEN AIP)
• MM-OVSeg: Multimodal Optical–SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
  Yimin Wei (University of Tokyo / RIKEN AIP)
  Aoran Xiao (RIKEN AIP)
  Hongruixuan Chen (The University of Tokyo)
  Junshi Xia (RIKEN AIP)
  Naoto Yokoya (University of Tokyo / RIKEN AIP)

Related Laboratories