No abstract

With the development of 3DTV, the conversion of existing 2D videos to 3D videos becomes an important component of 3D content production. One of the key steps in 2D to 3D conversion is how to generate a dense depth map. In this paper, we propose a novel depth extraction method based on motion and geometric information for 2D to 3D conversion, which consists of two major depth extraction modules, the depth from motion and depth from geometrical perspective. The H.264 motion estimation result is utilized and cooperates with moving object detection to diminish block effect and generates a motion-based depth map. On the other hand, a geometry-based depth map is generated by edge detection andHough transform. Finally, the motion-based depth map and the geometry-based depth map are integrated into one depth map by a depth fusion algorithm.

No abstract

Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate sparse but accurate depth measurements obtained from lidars to overcome the limitation of visual methods. To this end, we design a self-supervised visual-lidar odometry (Self-VLO) framework. It takes both monocular images and sparse depth maps projected from 3D lidar points as input, and produces pose and depth estimations in an end-to-end learning manner, without using any ground truth labels. To effectively fuse two modalities, we design a two-pathway encoder to extract features from visual and depth images and fuse the encoded features with those in decoders at multiple scales by our fusion module. We also adopt a siamese architecture and design an adaptively weighted flip consistency loss to facilitate the selfsupervised learning of our VLO. Experiments on the KITTI odometry benchmark show that the proposed approach outperforms all self-supervised visual or lidar odometries. It also performs better than fully supervised VOs, demonstrating the power of fusion.

No abstract