Self-supervised monocular depth estimation has been widely investigated and applied in previous works.However,existing methods suffer from texture-copy,depth drift,and incomplete structure.It is difficult for normal CNN networks to completely understand the relationship between the object and its surrounding environment.Moreover,it is hard to design the depth smoothness loss to balance depth smoothness and sharpness.To address these issues,we propose a coarse-to-fine method with a normalized convolutional block attention module(NCBAM).In the coarse estimation stage,we incorporate the NCBAM into depth and pose networks to overcome the texture-copy and depth drift problems.Then,we use a new network to refine the coarse depth guided by the color image and produce a structure-preserving depth result in the refinement stage.Our method can produce results competitive with state-of-the-art methods.Comprehensive experiments prove the effectiveness of our two-stage method using the NCBAM.

Yuanzhen Li;Fei Luo;Chunxia Xiao

School of Computer Science,Wuhan University,Wuhan 430072,China

计算可视媒体（英文）

[1]Yuanzhen Li;Fei Luo;Chunxia Xiao-.Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module)[J].计算可视媒体（英文）,2022(04):631-647

NCBAM

Self,supervised,coarse,monocular,depth,estimation,using,lightweight,attention,module,has,been,widely,investigated,applied,previous,However,existing,methods,suffer,from,texture,copy,drift,incomplete,structure,It,difficult,networks,completely,understand,relationship,between,object,its,surrounding,environment,Moreover,hard,design,smoothness,loss,balance,sharpness,To,address,these,issues,propose,normalized,convolutional,block,In,stage,incorporate,into,overcome,problems,Then,use,new,guided,by,color,image,produce,preserving,refinement,Our,can,results,competitive,state,art,Comprehensive,experiments,prove,effectiveness,our

0.532297