Starred repositories
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
This is the official repo of Panoptic SegFormer [CVPR'22]
Deformable ConvNets V2 (DCNv2) in PyTorch
Stereo vision based object detection for ADAS, autonomous vehicle
Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)
Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
Unpaired line drawing generation
Motion Retargeting Video Subjects
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
Learning Facial Representations from the Cycle-consistency of Face (ICCV 2021)
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
A framework for synthetic test data generation for computer vision with the Unreal Engine.
Pyramid Stereo Matching Network (CVPR2018)
GA-Net: Guided Aggregation Net for End-to-end Stereo Matching
[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.
Official code base of the BEVDet series .
[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes
[CVPR 2022] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).