Depth Based Semantic Scene Completion with Position Importance Aware Loss

01/29/2020
by   Yu Liu, et al.
14

Semantic Scene Completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hybrid network for SSC based on single depth. PALNet utilizes a two-stream network to extract both 2D and 3D features from multi-stages using fine-grained depth information to efficiently captures the context, as well as the geometric cues of the scene. Current methods for SSC treat all parts of the scene equally causing unnecessary attention to the interior of objects. To address this problem, we propose Position Aware Loss(PA-Loss) which is position importance aware while training the network. Specifically, PA-Loss considers Local Geometric Anisotropy to determine the importance of different positions within the scene. It is beneficial for recovering key details like the boundaries of objects and the corners of the scene. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed method and its superior performance. Models and Video demo can be found at: https://github.com/UniLauX/PALNet.

READ FULL TEXT

page 1

page 4

page 6

research
04/08/2021

Semantic Scene Completion via Integrating Instances and Scene in-the-Loop

Semantic Scene Completion aims at reconstructing a complete 3D scene wit...
research
02/17/2020

3D Gated Recurrent Fusion for Semantic Scene Completion

This paper tackles the problem of data fusion in the semantic scene comp...
research
02/27/2023

OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion

3D Semantic Scene Completion (SSC) can provide dense geometric and seman...
research
09/30/2019

Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

Geometric 3D scene classification is a very challenging task. Current me...
research
03/21/2022

Depth Completion using Geometry-Aware Embedding

Exploiting internal spatial geometric constraints of sparse LiDARs is be...
research
07/17/2017

Slanted Stixels: Representing San Francisco's Steepest Streets

In this work we present a novel compact scene representation based on St...
research
10/02/2019

Slanted Stixels: A way to represent steep streets

This work presents and evaluates a novel compact scene representation ba...

Please sign up or login with your details

Forgot password? Click here to reset