Канал: Chunhua Shen

Generating stories using diffusion models

Generating stories using diffusion models

泰坦尼克号 AIGC 版。

泰坦尼克号 AIGC 版。

Metric3D x DroidSLAM, kitti 2011 09 30 drive 0034

Metric3D x DroidSLAM, kitti 2011 09 30 drive 0034

3D street scene reconstruction for autonomous driving

3D street scene reconstruction for autonomous driving

Explainable Deep Few-shot Anomaly Detection with Deviation Networks

Explainable Deep Few-shot Anomaly Detection with Deviation Networks

Simple approaches to instance recognition, Nov 2021

Simple approaches to instance recognition, Nov 2021

3D Photography Using Monocular Depth Estimation

3D Photography Using Monocular Depth Estimation

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

Pose estimation using single-stage fully convolutional networks

Pose estimation using single-stage fully convolutional networks

Image and Video Matting

Image and Video Matting

Efficient Semantic Video Segmentation with Per-frame Inference

Efficient Semantic Video Segmentation with Per-frame Inference

Single RGB to 3D reconstruction

Single RGB to 3D reconstruction

Monocular Relative Depth Perception with Web Stereo Data Supervision

Monocular Relative Depth Perception with Web Stereo Data Supervision

Learning to Recover 3D Scene Shape from a Single Image

Learning to Recover 3D Scene Shape from a Single Image

BoxInst video

BoxInst video

SOLOv2 R101 video

SOLOv2 R101 video

video demo for keypoint detection

video demo for keypoint detection

Depth estimation from monocular images

Depth estimation from monocular images

Semantic segmentation on video

Semantic segmentation on video

Pose estimation

Pose estimation

Semantic segmentation on the cityscapes dataset

Semantic segmentation on the cityscapes dataset

Depth estimation on NYUDv2

Depth estimation on NYUDv2

Depth estimation on Kitti

Depth estimation on Kitti

FCOS object detection with a compact MobileNet-like backbone

FCOS object detection with a compact MobileNet-like backbone

GAN ICCV2017 Face landmark

GAN ICCV2017 Face landmark

Pixel labelling of street scenes using deep learning

Pixel labelling of street scenes using deep learning

face detection

face detection