Knowledge Commons of Institute of Automation，CAS
| Stereo Depth Estimation with Echoes | |
Zhang, Chenghao ; Tian, Kun; Ni, Bolin; Meng, Gaofeng; Fan, Bin; Zhang, Zhaoxiang; Pan, Chunhong
| |
| 2022-10 | |
| 会议名称 | European Conference on Computer Vision (ECCV) |
| 会议日期 | 2022.10.24 |
| 会议地点 | 以色列特拉维夫 |
| 摘要 | Stereo depth estimation is particularly amenable to local textured regions while echoes have good depth estimations for global textureless regions, thus the two modalities complement each other. Motivated by the reciprocal relationship between both modalities, in this paper, we propose an end-to-end framework named StereoEchoes for stereo depth estimation with echoes. A Cross-modal Volume Refinement module is designed to transfer the complementary knowledge of the audio modality to the visual modality at feature level. A Relative Depth Uncertainty Estimation module is further proposed to yield pixel-wise confidence for multimodal depth fusion at output space. As there is no dataset for this new problem, we introduce two Stereo-Echo datasets named Stereo-Replica and Stereo-Matterport3D for the first time. Remarkably, we show empirically that our StereoEchoes, on Stereo-Replica and Stereo-Matterport3D, outperforms stereo depth estimation methods by 25%/13.8% RMSE, and surpasses the state-of-the-art audio-visual depth prediction method by 25.3%/42.3% RMSE. |
| 语种 | 英语 |
| 七大方向——子方向分类 | 三维视觉 |
| 国重实验室规划方向分类 | 视觉信息处理 |
| 是否有论文关联数据集需要存交 | 否 |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.ia.ac.cn/handle/173211/51492 |
| 专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
| 通讯作者 | Meng, Gaofeng |
| 作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAIR, HK Institute of Science and Innovation, Chinese Academy of Sciences 4.University of Science and Technology Beijing |
| 推荐引用方式 GB/T 7714 | Zhang, Chenghao,Tian, Kun,Ni, Bolin,et al. Stereo Depth Estimation with Echoes[C],2022. |
| 条目包含的文件 | 下载所有文件 | |||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| 论文序号2_ECCV.pdf（1587KB） | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
修改评论