Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BA-Net: Dense Bundle Adjustment Network

About

This paper introduces a network architecture to solve the structure-from-motion (SfM) problem via feature-metric bundle adjustment (BA), which explicitly enforces multi-view geometry constraints in the form of feature-metric error. The whole pipeline is differentiable so that the network can learn suitable features that make the BA problem more tractable. Furthermore, this work introduces a novel depth parameterization to recover dense per-pixel depth. The network first generates several basis depth maps according to the input image and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA. The basis depth maps generator is also learned via end-to-end training. The whole system nicely combines domain knowledge (i.e. hard-coded multi-view geometry constraints) and deep learning (i.e. feature learning and basis depth maps learning) to address the challenging dense SfM problem. Experiments on large scale real data prove the success of the proposed method.

Chengzhou Tang, Ping Tan• 2018

Related benchmarks

TaskDatasetResultRank
Depth EstimationKITTI (Eigen split)
RMSE3.64
276
Depth EstimationScanNet (test)
Abs Rel0.161
65
Depth EstimationSun3D (test)
Abs Rel6
22
Depth EstimationScenes11 (test)
L1 Relative Error0.13
12
Pose EstimationMVS DeMoN version (test)
Rot Error3.499
8
Pose EstimationSun3D (test)
Rotation Error1.729
8
Pose EstimationScenes11 (test)
Rotation Error3.499
8
Video Depth EstimationScanNet (in-domain)
Abs Rel0.091
8
Two-view Depth EstimationScanNet (test)
Abs Rel0.161
8
Depth EstimationMVS DeMoN (test)
L1-rel0.08
7
Showing 10 of 11 rows

Other info

Follow for update