Attention attention everywhere: Monocular depth prediction with skip attention
Abstract Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single
RGB image. For both, the convolutional as well as the recent attention-based models …
RGB image. For both, the convolutional as well as the recent attention-based models …
Adabins: Depth estimation using adaptive bins
We address the problem of estimating a high quality dense depth map from a single RGB
input image. We start out with a baseline encoder-decoder convolutional neural network …
input image. We start out with a baseline encoder-decoder convolutional neural network …
Binsformer: Revisiting adaptive bins for monocular depth estimation
Monocular depth estimation (MDE) is a fundamental task in computer vision and has drawn
increasing attention. Recently, some methods reformulate it as a classification-regression …
increasing attention. Recently, some methods reformulate it as a classification-regression …
Depthformer: Exploiting long-range correlation and local information for accurate monocular depth estimation
This paper aims to address the problem of supervised monocular depth estimation. We start
with a meticulous pilot study to demonstrate that the long-range correlation is essential for …
with a meticulous pilot study to demonstrate that the long-range correlation is essential for …
P3depth: Monocular depth estimation with a piecewise planarity prior
Monocular depth estimation is vital for scene understanding and downstream tasks. We
focus on the supervised setup, in which ground-truth depth is available only at training time …
focus on the supervised setup, in which ground-truth depth is available only at training time …
From big to small: Multi-scale local planar guidance for monocular depth estimation
Estimating accurate depth from a single image is challenging because it is an ill-posed
problem as infinitely many 3D scenes can be projected to the same 2D scene. However …
problem as infinitely many 3D scenes can be projected to the same 2D scene. However …
Monocular depth estimation using laplacian pyramid-based depth residuals
With a great success of the generative model via deep neural networks, monocular depth
estimation has been actively studied by exploiting various encoder-decoder architectures …
estimation has been actively studied by exploiting various encoder-decoder architectures …
Vip-deeplab: Learning visual perception with depth-aware video panoptic segmentation
In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-
standing and challenging inverse projection problem in vision, which we model as restoring …
standing and challenging inverse projection problem in vision, which we model as restoring …
Multimodal end-to-end autonomous driving
A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to
drive towards a desired destination. Today, there are different paradigms addressing the …
drive towards a desired destination. Today, there are different paradigms addressing the …
Quadratic video interpolation
Video interpolation is an important problem in computer vision, which helps overcome the
temporal limitation of camera sensors. Existing video interpolation methods usually assume …
temporal limitation of camera sensors. Existing video interpolation methods usually assume …