Two-week challenge
We took the challenge of reading one paper a day for two weeks and here is the list of the papers we all read. For the sake of exactness, it was around 1 paper per day on average and we didn’t need to read the same papers, some people shared some papers but in general, we were fully free to choose.
After the 2 weeks, we made short meetings to share a very short summary of each of the papers
Here is the list of all papers discussed
-
GitHub - ISEE-Technology/CamVox: [ICRA2021] A low-cost SLAM system based on camera and Livox lidar.
-
A Review of Visual-LiDAR Fusion based Simultaneous Localization and Mapping
-
Blind Geometric Distortion Correction on Images Through Deep Learning
-
Self-supervised Monocular Depth Estimation with internal feature fusion
-
Recurrent Multi-View alignment network for unsupervised surface registration
-
Prototypical cross-attention network for multiple object tracking and segmentation
-
In-place scene labelling and understanding with implicit scene representation
-
Recurrent Multiframe single shot detector for video object detection
-
LoFTR: Detector-Free Local Feature Matching with Transformers
-
One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
-
Probabilistic Future Prediction for Video Scene Understanding
-
ORB-SLAM2
-
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
-
Orthographic Feature Transform for Monocular 3D Object Detection
-
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
-
Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve
-
Discrete Kalman Filter Tutorial
-
Relational inductive biases, deep learning, and graph networks (in progress)
-
Inductive Biases for Deep Learning of Higher-Level Cognition.
-
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks