Fast Scene Understanding for Autonomous Driving
Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this observation and inspired by recent works that tackle multiple tasks with a single integrated architecture, in this paper we present a real-time efficient implementation based on ENet that solves three autonomous driving related tasks at once: semantic scene segmentation, instance segmentation and monocular depth estimation. Our approach builds upon a branched ENet architecture with a shared encoder but different decoder branches for each of the three tasks. The presented method can run at 21 fps at a resolution of 1024x512 on the Cityscapes dataset without sacrificing accuracy compared to running each task separately.
Code (1)
Tasks
Autonomous DrivingDecoderDepth EstimationInstance SegmentationMonocular Depth EstimationScene SegmentationScene UnderstandingSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic …
Autonomous DrivingBench2DriveTrajectory PlanningPredicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving
The autonomous driving field has seen remarkable advancements in various topics, such as object recognition, trajectory prediction, and motion planning. However, current approaches face limitations in effectively compreh…
Autonomous DrivingKnowledge GraphsMotion PlanningObject Recognition+2GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
Self-supervised learning has made substantial strides in image processing, while visual pre-training for autonomous driving is still in its infancy. Existing methods often focus on learning geometric scene information wh…
3D Object DetectionAutonomous DrivingGPUNeRF+4LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving
Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on o…
Scene UnderstandingAutonomous DrivingScene RecognitionVLP: Vision Language Planning for Autonomous Driving
Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, t…
Autonomous DrivingMotion PlanningScene Understanding