PSFormer: Point Transformer for 3D Salient Object Detection

10/28/2022
by   Baian Chen, et al.
0

We propose PSFormer, an effective point transformer model for 3D salient object detection. PSFormer is an encoder-decoder network that takes full advantage of transformers to model the contextual information in both multi-scale point- and scene-wise manners. In the encoder, we develop a Point Context Transformer (PCT) module to capture region contextual features at the point level; PCT contains two different transformers to excavate the relationship among points. In the decoder, we develop a Scene Context Transformer (SCT) module to learn context representations at the scene level; SCT contains both Upsampling-and-Transformer blocks and Multi-context Aggregation units to integrate the global semantic and multi-level features from the encoder into the global scene context. Experiments show clear improvements of PSFormer over its competitors and validate that PSFormer is more robust to challenging cases such as small objects, multiple objects, and objects with complex structures.

READ FULL TEXT

page 1

page 2

page 4

research
04/12/2020

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

In this paper, we address the 3D object detection task by capturing mult...
research
05/05/2020

Multi-interactive Encoder-decoder Network for RGBT Salient Object Detection

RGBT salient object detection (SOD) aims to segment the common prominent...
research
02/18/2019

Contextual Encoder-Decoder Network for Visual Saliency Prediction

Predicting salient regions in natural images requires the detection of o...
research
07/21/2021

Multi-Stream Transformers

Transformer-based encoder-decoder models produce a fused token-wise repr...
research
09/13/2022

CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection

Existing deep learning-based 3D object detectors typically rely on the a...
research
08/17/2021

Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net

Existing salient object detection (SOD) methods mainly rely on CNN-based...
research
08/23/2021

Improving 3D Object Detection with Channel-wise Transformer

Though 3D object detection from point clouds has achieved rapid progress...

Please sign up or login with your details

Forgot password? Click here to reset