Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data. We investigate specifically the impact of object placement distribution, keeping all other aspects of synthetic data fixed. Our experiment, training a 3D vehicle detection model in CARLA and testing on KITTI, demonstrates a substantial improvement resulting from improving the object placement distribution.
Code (1)
Tasks
Objectobject-detectionObject Detectionvehicle detectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World
Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the…
Dataset GenerationAnyPlace: Learning Generalized Object Placement for Robot Manipulation
Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. To address this, we propose AnyPlace, a two-stage method trained entirely on synthetic d…
ObjectPose PredictionRobot ManipulationLearning to Estimate Pose and Shape of Hand-Held Objects from RGB Images
We develop a system for modeling hand-object interactions in 3D from RGB images that show a hand which is holding a novel object from a known category. We design a Convolutional Neural Network (CNN) for Hand-held Object …
Image-to-Image TranslationObjectTranslationRPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud
We introduce RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape. RPM-Net is a novel Re…
DecoderSemantic SegmentationBlendTorch: A Real-Time, Adaptive Domain Randomization Library
Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the succe…
object-detectionObject Detection