paper-with-me

Papers

Single-Image Depth Prediction Makes Feature Matching Easier

2020-08-21 · Carl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl, Gabriel Brostow

Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve appearance invariance by choosing better local feature points or by leveraging outside information, have come with pre-requisites that made some of them impractical. In this paper, we propose a surprisingly effective enhancement to local feature extraction, which improves matching. We show that CNN-based depths inferred from single RGB images are quite helpful, despite their flaws. They allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.

📄 PDF Abstract BibTeX arXiv:2008.09497

Code (1)

nianticlabs/rectified-features 공식 구현

Tasks

Depth EstimationDepth PredictionPrediction

Similar Papers 제목 키워드 기반

Single-Image Depth Prediction Makes Feature Matching Easier

2020-08-01 · ECCV 2020 8 · Carl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl 외

Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attemp…

Depth EstimationDepth PredictionPrediction

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

2014-06-09 · NeurIPS 2014 12 · David Eigen, Christian Puhrsch, Rob Fergus

Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a single image is less straightfo…

3D geometryMonocular Depth Estimation

SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation

2021-06-19 · CVPR 2021 1 · Giovanni Pintore, Marco Agus, Eva Almansa, Jens Schneider 외

We introduce a novel deep neural network to estimate a depth map from a single monocular indoor panorama. The network directly works on the equirectangular projection, exploiting the properties of indoor 360 images. …

Depth Estimation

Boundary-induced and scene-aggregated network for monocular depth prediction

2021-02-26 · Feng Xue, Junfeng Cao, Yu Zhou, Fei Sheng 외

Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the performance of this task has made great improve…

Depth EstimationDepth PredictionScene Understanding

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

2023-02-13 · Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte 외

We introduce VA-DepthNet, a simple, effective, and accurate deep neural network approach for the single-image depth prediction (SIDP) problem. The proposed approach advocates using classical first-order variational const…

Depth EstimationDepth PredictionMonocular Depth Estimation