ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass

Abstract

Direct contour regression for instance segmentation is a challenging task. Previous works usually achieve it by learning to progressively refine the contour prediction or adopting a shape representation with limited expressiveness. In this work, we argue that the difficulty in regressing the contour points in one pass is mainly due to the ambiguity when discretizing a smooth contour into a polygon. To address the ambiguity, we propose a novel differentiable rendering-based approach named \textbf{ContourRender}. During training, it first predicts a contour generated by an invertible shape signature, and then optimizes the contour with the more stable silhouette by converting it to a contour mesh and rendering the mesh to a 2D map. This method significantly improves the quality of contour without iterations or cascaded refinements. Moreover, as optimization is not needed during inference, the inference speed will not be influenced. Experiments show the proposed ContourRender outperforms all the contour-based instance segmentation approaches on COCO, while stays competitive with the iteration-based state-of-the-art on Cityscapes. In addition, we specifically select a subset from COCO val2017 named COCO ContourHard-val to further demonstrate the contour quality improvements. Codes, models, and dataset split will be released.

arXiv commentTech report

References in corpus (17)

• YOLOv3: An Incremental Improvement
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCOS: Fully Convolutional One-Stage Object Detection
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• SOLOv2: Dynamic and Fast Instance Segmentation
• Deformable Convolutional Networks
• Path Aggregation Network for Instance Segmentation
• Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
• Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
• Annotating Object Instances with a Polygon-RNN
• Fast Interactive Object Annotation with Curve-GCN
• Unsupervised Training for 3D Morphable Model Regression
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• DARNet: Deep Active Ray Network for Building Segmentation
• Explicit Shape Encoding for Real-Time Instance Segmentation
• End to End Trainable Active Contours via Differentiable Rendering
• Deep Active Contours Using Locally Controlled Distance Vector Flow