1. 2023/04/06

  2. Segment Anything Demo

    Raw Image Segmentation (mode: Everything) RoI road sign, China ETC sign, overlapped cars pedestrain, indoor parking area image blurring, cars in shadow, railway potholes (drivable) holes (non-drivable)      

    2023/04/06 Vision Foundation Model

  3. BEVFusion

    2022/10/17 PaperNotes

  4. Lift, Splat, Shoot

    Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D

    2022/10/15 PaperNotes

  5. Detr3d

    We link 2D feature extraction and 3D object prediction via geometric back-projection with camera transfor-mation matrices.

    2022/10/08

  6. UniFormer

    论文名称:UniFormer: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird’s-Eye-View

    2022/10/04 PaperNotes

  7. Polar-DETR:基于环视摄像系统的3D检测

    论文名称:Polar Parametrization for Vision-based Surround-View 3D Detection

    2022/10/04 PaperNotes Freespace

  8. Occupancy Network Tesla AI Reference

    论文名称:Occupancy Networks: Learning 3D Reconstruction in Function Space

    2022/10/04 PaperNotes Freespace

  9. Exploring the Effects of Data Augmentation for Drivable Area Segmentation

    论文名称:Exploring the Effects of Data Augmentation for Drivable Area Segmentation,是一篇Cityscapes数据集上构建freespace segmentation的技术报告。研究了语义分割模型的数据增强方法,提出了一个魔改 UNet + CBAM 模型,在 Cityscapes 验证,但没有说明是如何在 Cityscapes 构建 drivable area ground truth 的。

    2022/10/03 PaperNotes Freespace

  10. 3D卷积神经网络的架构搜索(二)

    AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures (Google 作者AJ 发表于ICLR2020)

    2020/09/11 NAS ActionRecognition PaperNotes