no code implementations • 10 Apr 2024 • Runfa Li, Upal Mahbub, Vasudev Bhaskaran, Truong Nguyen
MonoSelfRecon is not restricted by specific model design, which can be used to any models with voxel-SDF for purely self-supervised manner.
1 code implementation • 24 Nov 2021 • Runfa Li, Truong Nguyen
Our real-scale scene flow estimation outperforms all state-of-the-art monocular-image based works recovered to real scale by ground truth, and is comparable to LiDAR approaches.
no code implementations • 24 Nov 2021 • Runfa Li, Truong Nguyen
In 3D Detection module, the depth estimation is projected into 3D space to generate "Pseudo-LiDAR" point cloud, where LiDAR-based 3D detector can be leveraged on point cloud for vehicular 3D detection and localization.