Timezone: »
As a basic component of SE(3)-equivariant deep feature learning, steerable convolution has recently demonstrated its advantages for 3D semantic analysis. The advantages are, however, brought by expensive computations on dense, volumetric data, which prevent its practical use for efficient processing of 3D data that are inherently sparse. In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance. Based on SS-Conv, we propose a general pipeline for precise estimation of object poses, wherein a key design is a Feature-Steering module that takes the full advantage of SE(3)-equivariance and is able to conduct an efficient pose refinement. To verify our designs, we conduct thorough experiments on three tasks of 3D object semantic analysis, including instance-level 6D pose estimation, category-level 6D pose and size estimation, and category-level 6D pose tracking. Our proposed pipeline based on SS-Conv outperforms existing methods on almost all the metrics evaluated by the three tasks. Ablation studies also show the superiority of our SS-Conv over alternative convolutions in terms of both accuracy and efficiency. Our code is released publicly at https://github.com/Gorilla-Lab-SCUT/SS-Conv.
Author Information
Jiehong Lin (South China University of Technology)
Hongyang Li (South China University Of Technology)
Ke Chen (South China University of Technology)
Jiangbo Lu (Shenzhen SmartMore Technology Co., Ltd.)
Kui Jia (South China University of Technology)
More from the Same Authors
-
2022 Poster: Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering »
Yongyi Su · Xun Xu · Kui Jia -
2022 Poster: TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition »
Yongwei Chen · chen rui · Jiabao Lei · Yabin Zhang · Kui Jia -
2022 Spotlight: Lightning Talks 4B-3 »
Zicheng Zhang · Mancheng Meng · Antoine Guedon · Yue Wu · Wei Mao · Zaiyu Huang · Peihao Chen · Shizhe Chen · Yongwei Chen · Keqiang Sun · Yi Zhu · chen rui · Hanhui Li · Dongyu Ji · Ziyan Wu · miaomiao Liu · Pascal Monasse · Yu Deng · Shangzhe Wu · Pierre-Louis Guhur · Jiaolong Yang · Kunyang Lin · Makarand Tapaswi · Zhaoyang Huang · Terrence Chen · Jiabao Lei · Jianzhuang Liu · Vincent Lepetit · Zhenyu Xie · Richard I Hartley · Dinggang Shen · Xiaodan Liang · Runhao Zeng · Cordelia Schmid · Michael Kampffmeyer · Mathieu Salzmann · Ning Zhang · Fangyun Wei · Yabin Zhang · Fan Yang · Qifeng Chen · Wei Ke · Quan Wang · Thomas Li · qingling Cai · Kui Jia · Ivan Laptev · Mingkui Tan · Xin Tong · Hongsheng Li · Xiaodan Liang · Chuang Gan -
2022 Spotlight: TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition »
Yongwei Chen · chen rui · Jiabao Lei · Yabin Zhang · Kui Jia -
2020 Poster: LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond »
Wenbo Li · Kun Zhou · Lu Qi · Nianjuan Jiang · Jiangbo Lu · Jiaya Jia