Pith. sign in

REVIEW 6 cited by

Deep Image Homography Estimation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1606.03798 v1 pith:46N5F25S submitted 2016-06-13 cs.CV

Deep Image Homography Estimation

classification cs.CV
keywords homographydeepnetworkimageestimationimagesapproachconvolutional
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present a deep convolutional neural network for estimating the relative homography between a pair of images. Our feed-forward network has 10 layers, takes two stacked grayscale images as input, and produces an 8 degree of freedom homography which can be used to map the pixels from the first image to the second. We present two convolutional neural network architectures for HomographyNet: a regression network which directly estimates the real-valued homography parameters, and a classification network which produces a distribution over quantized homographies. We use a 4-point homography parameterization which maps the four corners from one image into the second image. Our networks are trained in an end-to-end fashion using warped MS-COCO images. Our approach works without the need for separate local feature detection and transformation estimation stages. Our deep models are compared to a traditional homography estimator based on ORB features and we highlight the scenarios where HomographyNet outperforms the traditional technique. We also describe a variety of applications powered by deep homography estimation, thus showcasing the flexibility of a deep learning approach.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark

    cs.CV 2026-04 unverdicted novelty 7.0

    GSCNet with FDAM and SGCM modules plus the URTF benchmark improves fine-grained semantic segmentation on unaligned UAV RGBT images.

  2. SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios

    cs.CV 2026-06 unverdicted novelty 6.0

    SA-Homo introduces a hierarchical scale-adaptive homography estimation framework with SDBM, MLAC, CSMB, and IHERM modules plus the HMSA dataset that claims robust performance under up to 8x scale discrepancies.

  3. CamFlow+: Hybrid Motion Bases for 2D Camera Motion Estimation with Stabilization Applications

    cs.CV 2026-06 unverdicted novelty 6.0

    CamFlow+ is a hybrid-basis framework for 2D camera motion estimation that relaxes single-plane constraints using physical, stochastic, and depth-derived bases, with evaluation on a masked camera-motion benchmark and s...

  4. Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views

    cs.CV 2025-11 unverdicted novelty 6.0

    Uni-Hand forecasts 2D/3D hand waypoints, head motion, and contact states in egocentric views using vision-language fusion and dual-branch diffusion, with new benchmarks for downstream robotics and action tasks.

  5. Homographic Navigation: Geometry-Driven Camera Guidance for Deterministic Planar Capture

    cs.CV 2026-06 unverdicted novelty 5.0

    Homographic navigation uses homography-driven synthetic data generation and a two-pass keypoint model with Stable Warp training to achieve accurate planar alignment from minimal supervision.

  6. Towards Seamless Lunar Mosaics: Deep Radiometric Normalization for Cross-Sensor Orbital Imagery Using Chandrayaan-2 TMC Data

    cs.CV 2026-04 unverdicted novelty 4.0

    A cGAN with U-Net generator and PatchGAN discriminator learns radiometric normalization from Chandrayaan-2 TMC imagery to LROC WAC reference, yielding improved tonal uniformity and fewer seams than histogram matching.