Fast Depth Estimation for View Synthesis
This work addresses the need for fast and accurate depth estimation in 3D vision applications like view synthesis, offering significant performance gains over existing methods.
The paper tackles the challenging problem of accurate depth estimation from stereo images for view synthesis, proposing a novel learning-based framework that achieves a 45% improvement in depth estimation accuracy and a 34% improvement in view synthesis quality while being up to 10 times faster than state-of-the-art methods.
Disparity/depth estimation from sequences of stereo images is an important element in 3D vision. Owing to occlusions, imperfect settings and homogeneous luminance, accurate estimate of depth remains a challenging problem. Targetting view synthesis, we propose a novel learning-based framework making use of dilated convolution, densely connected convolutional modules, compact decoder and skip connections. The network is shallow but dense, so it is fast and accurate. Two additional contributions -- a non-linear adjustment of the depth resolution and the introduction of a projection loss, lead to reduction of estimation error by up to 20% and 25% respectively. The results show that our network outperforms state-of-the-art methods with an average improvement in accuracy of depth estimation and view synthesis by approximately 45% and 34% respectively. Where our method generates comparable quality of estimated depth, it performs 10 times faster than those methods.