Unsupervised Monocular Depth Learning in Dynamic Scenes
We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including methods that require semantic input. Code is at https://github.com/google-research/google-research/tree/master/depth_and_motion_learning .
Code (5)
Tasks
Depth EstimationDepth PredictionMonocular Depth EstimationTranslationUnsupervised Monocular Depth EstimationSimilar Papers 제목 키워드 기반
Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists li…
Depth EstimationMotion SegmentationDynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object moti…
Depth EstimationMonocular Depth EstimationMotion SegmentationSegmentation+1Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics
We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D mo…
Depth And Camera MotionDepth EstimationMonocular Depth EstimationMotion EstimationRM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to inc…
DecoderDepth EstimationMonocular Depth EstimationUnsupervised Monocular Depth EstimationMining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation
This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction los…
Depth EstimationImage ReconstructionMonocular Depth EstimationMotion Estimation