A comprehensive survey of neural architecture search: Challenges and solutions
Deep learning has made substantial breakthroughs in many fields due to its powerful
automatic representation capabilities. It has been proven that neural architecture design is …
automatic representation capabilities. It has been proven that neural architecture design is …
Robustness-aware 3d object detection in autonomous driving: A review and outlook
In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …
accurately assessing the state of the surrounding environment, thereby enabling informed …
Iterative geometry encoding volume for stereo matching
Abstract Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …
Practical stereo matching via cascaded recurrent network with adaptive correlation
J Li, P Wang, P Xiong, T Cai, Z Yan… - Proceedings of the …, 2022 - openaccess.thecvf.com
With the advent of convolutional neural networks, stereo matching algorithms have recently
gained tremendous progress. However, it remains a great challenge to accurately extract …
gained tremendous progress. However, it remains a great challenge to accurately extract …
Unifying flow, stereo and depth estimation
We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …
Attention concatenation volume for accurate and efficient stereo matching
Stereo matching is a fundamental building block for many vision and robotics applications.
An informative and concise cost volume representation is vital for stereo matching of high …
An informative and concise cost volume representation is vital for stereo matching of high …
Raft-stereo: Multilevel recurrent field transforms for stereo matching
We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical
flow network RAFT [35]. We introduce multi-level convolutional GRUs, which more efficiently …
flow network RAFT [35]. We introduce multi-level convolutional GRUs, which more efficiently …
Cfnet: Cascade and fused cost volume for robust stereo matching
Recently, the ever-increasing capacity of large-scale annotated datasets has led to profound
progress in stereo matching. However, most of these successes are limited to a specific …
progress in stereo matching. However, most of these successes are limited to a specific …
Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers
Stereo depth estimation relies on optimal correspondence matching between pixels on
epipolar lines in the left and right images to infer depth. In this work, we revisit the problem …
epipolar lines in the left and right images to infer depth. In this work, we revisit the problem …
ZeroNAS: Differentiable generative adversarial networks search for zero-shot learning
In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by
generative adversarial networks (GAN). To compensate for the lack of training samples in …
generative adversarial networks (GAN). To compensate for the lack of training samples in …