fundamentalvision

BEVFormer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Uni-Perceiver

Auto-Seg-Loss

Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Parameterized-AP-Loss

UniGrad

Siamese-Image-Modeling

fundamentalvision.github.io