Skip to content

Code release for ECCV 2022 paper "Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features".

Notifications You must be signed in to change notification settings

wufeim/6d_pose_eccv22

Repository files navigation

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features

PyTorch implementation for robust category-level 6D pose estimation with coarse-to-fine rendering of neural features.

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features
Wufei Ma, Angtian Wang, Alan Yuille, Adam Kortylewski
In European Conference on Computer Vision (ECCV) 2022
[Paper]

Installation

Follow requirements.txt to setup the environment.

Preparation

  1. Prepare PASCAL3D+ with ./prepare_data.sh.

Demo

6D pose estimation with multi-object reasoning:

CUDA_VISIBLE_DEVICES=0 python3 tools/demo.py

About

Code release for ECCV 2022 paper "Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features".

Resources

Stars

Watchers

Forks