Benchmarks
Greatest papers with code
Structure-From-Motion Revisited
Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections.
Fine-tuning CNN Image Retrieval with No Human Annotation
• filipradenovic/cnnimageretrieval-pytorch
• 
We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
• filipradenovic/cnnimageretrieval-pytorch
•
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
Ranked #5 on
Image Retrieval
on Oxf5k
Consistent Video Depth Estimation
• facebookresearch/consistent_depth
•
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video.
MegaDepth: Learning Single-View Depth Prediction from Internet Photos
CVPR 2018
• zhengqili/MegaDepth
•
We validate the use of large amounts of Internet data by showing that models trained on MegaDepth exhibit strong generalization-not only to novel scenes, but also to other diverse datasets including Make3D, KITTI, and DIW, even when no images from those datasets are seen during training.
DEPTH ESTIMATION SEMANTIC SEGMENTATION STRUCTURE FROM MOTION
DeMoN: Depth and Motion Network for Learning Monocular Stereo
CVPR 2017
• lmb-freiburg/demon
• 
In this paper we formulate structure from motion as a learning problem.
DEPTH AND CAMERA MOTION OPTICAL FLOW ESTIMATION STRUCTURE FROM MOTION
A Photogrammetry-based Framework to Facilitate Image-based Modeling and Automatic Camera Tracking
We propose a framework that extends Blender to exploit Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques for image-based modeling tasks such as sculpting or camera and motion tracking.
C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion
ICCV 2019
• facebookresearch/c3dpo_nrsfm
•
We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images.
Graph-Based Parallel Large Scale Structure from Motion
After local reconstructions, we construct a minimum spanning tree (MinST) to find accurate similarity transformations.
DeepV2D: Video to Depth with Differentiable Structure from Motion
ICLR 2020
• princeton-vl/DeepV2D
•
We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video.
DEPTH ESTIMATION MOTION ESTIMATION OPTICAL FLOW ESTIMATION STEREO MATCHING HAND STRUCTURE FROM MOTION