Browse > Computer Vision > Perception

Perception

123 papers with code · Computer Vision

State-of-the-art leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers with code

Cycle-IR: Deep Cyclic Image Retargeting

9 May 2019mintanwei/Cycle-IR

Our idea is built on the reverse mapping from the retargeted images to the given input images.

PERCEPTION

6
09 May 2019

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

18 Apr 2019StanfordVL/MinkowskiEngine

To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space.

PERCEPTION SEMANTIC SEGMENTATION

198
18 Apr 2019

End-to-End Robotic Reinforcement Learning without Reward Engineering

16 Apr 2019avisingh599/reward-learning-rl

In this paper, we propose an approach for removing the need for manual engineering of reward specifications by enabling a robot to learn from a modest number of examples of successful outcomes, followed by actively solicited queries, where the robot shows the user a state and asks for a label to determine whether that state represents successful completion of the task.

PERCEPTION

108
16 Apr 2019

Towards Safety Verification of Direct Perception Neural Networks

9 Apr 2019dependable-ai/nn-dependability-kit

We study the problem of safety verification of direct perception neural networks, which take camera images as inputs and produce high-level features for autonomous vehicles to make control decisions.

AUTONOMOUS VEHICLES PERCEPTION

19
09 Apr 2019

Kervolutional Neural Networks

2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019) 2019 gan3sh500/kervolution-pytorch

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.

PERCEPTION

6
08 Apr 2019

Kervolutional Neural Networks

2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019) 2019 gan3sh500/kervolution-pytorch

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.

PERCEPTION

6
08 Apr 2019

3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization

5 Apr 2019zswang666/Stereo-LiDAR-CCVNorm

The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception.

DEPTH COMPLETION PERCEPTION STEREO MATCHING

23
05 Apr 2019

Bridging Adversarial Robustness and Gradient Interpretability

27 Mar 20191202kbs/Robustness-and-Interpretability

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples.

PERCEPTION

16
27 Mar 2019

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

20 Mar 2019Microsoft/Deep3DFaceReconstruction

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce.

3D FACE RECONSTRUCTION PERCEPTION

98
20 Mar 2019

Kernel-based Translations of Convolutional Networks

19 Mar 2019cjones6/yesweckn

Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods.

PERCEPTION

1
19 Mar 2019