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

## TL;DR

EdgeNet introduces a novel method for semantic scene completion from a single RGB-D image by encoding color information with edge detection and a new neural network architecture, achieving significant performance improvements.

## Contribution

The paper proposes a new encoding strategy for color in 3D using edge detection and introduces EdgeNet, an end-to-end neural network for improved semantic scene completion.

## Key findings

- Achieved 6.9% improvement over state-of-the-art on real data.
- Effectively fuses depth and edge information for better 3D scene understanding.
- Demonstrates the effectiveness of edge-based color encoding in 3D semantic tasks.

## Abstract

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.