Notably, our solution named LiteDepth ranks 2nd in the MAI&AIM2022 Monocular Depth Estimation Challenge}, with a si-RMSE of 0. 311, an RMSE of 3. 79, and the inference time is 37$ms$ tested on the Raspberry Pi 4.
Recently, AutoAlign presents a learnable paradigm in combining these two modalities for 3D object detection.
However, caused by severe domain gaps (e. g., the field of view (FOV), pixel size, and object size among datasets), Mono3D detectors have difficulty in generalization, leading to drastic performance degradation on unseen domains.
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding.
Based on this, we develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain.
This paper aims to address the problem of supervised monocular depth estimation.
Ranked #1 on Monocular Depth Estimation on KITTI Eigen split
This map enables our model to automate the alignment of non-homogenous features in a dynamic and data-driven manner.
To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks.
Extensive experiments on MS COCO benchmark show that our approach can lead to 2. 0 mAP, 2. 4 mAP and 2. 2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead.
Simulations based on these models suggest that the bit-error rate of devices are highly non-uniform across the memory array.
This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020.
In this technical report, we present our solutions of Waymo Open Dataset (WOD) Challenge 2020 - 2D Object Track.