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

EdgeNet: Semantic Scene Completion from a Single RGB-D Image

About

Semantic scene completion is the task of predicting a complete 3D representation of volumetric occupancy with corresponding semantic labels for a scene from a single point of view. Previous works on Semantic Scene Completion from RGB-D data used either only depth or depth with colour by projecting the 2D image into the 3D volume resulting in a sparse data representation. In this work, we present a new strategy to encode colour information in 3D space using edge detection and flipped truncated signed distance. We also present EdgeNet, a new end-to-end neural network architecture capable of handling features generated from the fusion of depth and edge information. Experimental results show improvement of 6.9% over the state-of-the-art result on real data, for end-to-end approaches.

Aloisio Dourado, Teofilo Emidio de Campos, Hansung Kim, Adrian Hilton• 2019

Related benchmarks

TaskDatasetResultRank
Semantic Scene CompletionNYU v2 (test)
Ceiling Error3.2
72
Scene CompletionNYU v2 (test)
mIoU57.9
48
Semantic Scene CompletionSUNCG (test)
Acc (Ceiling)97.2
33
Scene CompletionSUNCG (test)
IoU85.1
28
Showing 4 of 4 rows

Other info

Follow for update