|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
To address these challenges, we present ClearGrasp -- a deep learning approach for estimating accurate 3D geometry of transparent objects from a single RGB-D image for robotic manipulation.
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Ranked #5 on Real-Time Semantic Segmentation on NYU Depth v2
Visual perception entails solving a wide set of tasks (e. g., object detection, depth estimation, etc).
Ranked #1 on Surface Normals Estimation on Taskonomy
We observe many continuous output problems in computer vision are naturally contained in closed geometrical manifolds, like the Euler angles in viewpoint estimation or the normals in surface normal estimation.
We present a dataset of $360^o$ images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation.
We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction.
We present the Creative Flow+ Dataset, the first diverse multi-style artistic video dataset richly labeled with per-pixel optical flow, occlusions, correspondences, segmentation labels, normals, and depth.
3D CHARACTER ANIMATION FROM A SINGLE PHOTO DEPTH ESTIMATION IMAGE ANIMATION OBJECT TRACKING OPTICAL FLOW ESTIMATION STYLE GENERALIZATION SURFACE NORMALS ESTIMATION VIDEO STYLE TRANSFER VIDEO UNDERSTANDING
Ideally, this results in images from two domains that present shared information to the primary network.
Ranked #1 on Monocular Depth Estimation on Make3D