3D Detection | 3D Face Modeling | 3D Human Reconstruction | 3D Object Detection | 3D Shape Correspondence | 3D Shape Generation | 3D Shape Reconstruction | Activity Recognition | Agentic AI | Application | Biometrics | Body Matching | Camera Calibration | Camera+LiDAR+Radar | Data Imputation | Database | Dataset | Deepfake | Depth Completion | Depth Estimation | Depth Prediction | Domain Adaptation | Expression Recognition | Face Alignment | Face Antispoofing | Face Deidentification | Face Recognition | Face Reconstruction | Face Relighting | Face Synthesis | Forecasting | Gait Recognition | Generic Object 3D Reconstruction | Human Motion | Human Recognition | Image Alignment | Image Manipulation | Image Segmentation | Low-level Vision | Medical Imaging | Motion Compensation | Multi-modality | Multimedia Retrieval | Object Detection | Object Re-Identification | Pedestrian Detection | Person Re-identification | Plant Vision | Semantic Segmentation | Surveillance | Tracking | Typing Behavior | Vision-language

3D Detection

2026

  • RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection
    Zhihao Zhang, Gengwei Zhang, Tianlong Chen, Xiaoming Liu
    Proceeding of Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026), Atlanta, GA, Dec. 2026
    Bibtex | arXiv
    • @inproceedings{ refineany3d-depth-refinement-as-semantic-alignment-for-monocular-3d-detection,
      author = { Zhihao Zhang and Gengwei Zhang and Tianlong Chen and Xiaoming Liu },
      title = { RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection },
      booktitle = { Proceeding of Fortieth Conference on Neural Information Processing Systems },
      address = { Atlanta, GA },
      month = { December },
      year = { 2026 },
    }
  • Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation
    Zhihao Zhang, Abhinav Kumar, Huaizhi Qu, Tianlong Chen, Xiaoming Liu
    Proceeding of Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026), Atlanta, GA, Dec. 2026
    Bibtex
    • @inproceedings{ rethinking-geometric-depth-in-monocular-3d-object-detection-a-projection-consistent-reformulation,
      author = { Zhihao Zhang and Abhinav Kumar and Huaizhi Qu and Tianlong Chen and Xiaoming Liu },
      title = { Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation },
      booktitle = { Proceeding of Fortieth Conference on Neural Information Processing Systems },
      address = { Atlanta, GA },
      month = { December },
      year = { 2026 },
    }