About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

BlenderProc

25 Oct 2019DLR-RM/BlenderProc

BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.

3D OBJECT RECOGNITION DEPTH IMAGE ESTIMATION POSE ESTIMATION SEMANTIC SEGMENTATION SURFACE NORMALS ESTIMATION

ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation

6 Oct 2019Shreeyak/cleargrasp

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.

DEPTH COMPLETION MONOCULAR DEPTH ESTIMATION SURFACE NORMALS ESTIMATION TRANSPARENT OBJECT DEPTH ESTIMATION TRANSPARENT OBJECT DETECTION

Robust Learning Through Cross-Task Consistency

7 Jun 2020EPFL-VILAB/XTConsistency

Visual perception entails solving a wide set of tasks, e. g., object detection, depth estimation, etc.

3D RECONSTRUCTION DEPTH ESTIMATION MULTI-TASK LEARNING OBJECT DETECTION SURFACE NORMALS ESTIMATION

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

CVPR 2019 leoshine/Spherical_Regression

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.

3D ROTATION ESTIMATION SURFACE NORMALS ESTIMATION VIEWPOINT ESTIMATION

$360^o$ Surface Regression with a Hyper-Sphere Loss

16 Sep 2019VCL3D/SphericalViewSynthesis

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.

SURFACE NORMALS ESTIMATION

How Well Do Self-Supervised Models Transfer?

26 Nov 2020linusericsson/ssl-transfer

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.

FEW-SHOT LEARNING FINE-GRAINED IMAGE RECOGNITION IMAGE CLASSIFICATION REPRESENTATION LEARNING SELF-SUPERVISED LEARNING SEMANTIC SEGMENTATION SURFACE NORMALS ESTIMATION

Creative Flow+ Dataset

CVPR 2019 creativefloworg/creativeflow

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