Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel's direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.
Code (0)
등록된 구현이 없습니다.
Tasks
Instance SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation
In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our ta…
Amodal Instance SegmentationInstance SegmentationSegmentationSemantic SegmentationDepth-wise layering of 3d images using dense depth maps: a threshold based approach
Image segmentation has long been a basic problem in computer vision. Depth-wise Layering is a kind of segmentation that slices an image in a depth-wise sequence unlike the conventional image segmentation problems dealing…
Image SegmentationSegmentationSemantic SegmentationPointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm oft…
Autonomous DrivingSDOD:Real-time Segmenting and Detecting 3D Object by Depth
Most existing instance segmentation methods only focus on improving performance and are not suitable for real-time scenes such as autonomous driving. This paper proposes a real-time framework that segmenting and detectin…
Autonomous DrivingInstance Segmentationobject-detectionObject Detection+2SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting
Single image 3D photography enables viewers to view a still image from novel viewpoints. Recent approaches combine monocular depth networks with inpainting networks to achieve compelling results. A drawback of these tech…
Image Matting