paper-with-me

홈 › Papers

Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models

2023-05-24 · Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg, Yunpeng Liu, Matthew Niedoba, Xiaoxuan Liang, Dylan Green, Justice Sefas, Jonathan Wilder Lavington, Frank Wood, Adam Scibior

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.

📄 PDF Abstract BibTeX arXiv:2305.14621

Code (1)

inverted-ai/object-detection 공식 구현

Tasks

Objectobject-detectionObject Detectionvehicle detection

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
CARLA CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban…

Similar Papers 제목 키워드 기반

MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World

2025-04-21 · CVPR 2025 1 · Ankit Dhiman, Manan Shah, R Venkatesh Babu

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 Generation

AnyPlace: Learning Generalized Object Placement for Robot Manipulation

2025-02-06 · Yuchi Zhao, Miroslav Bogdanovic, Chengyuan Luo, Steven Tohme 외

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 Manipulation

Learning to Estimate Pose and Shape of Hand-Held Objects from RGB Images

2019-03-08 · Mia Kokic, Danica Kragic, Jeannette Bohg

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 TranslationObjectTranslation

RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud

2020-06-26 · Zihao Yan, Ruizhen Hu, Xingguang Yan, Luanmin Chen 외

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 Segmentation

BlendTorch: A Real-Time, Adaptive Domain Randomization Library

2020-10-06 · Christoph Heindl, Lukas Brunner, Sebastian Zambal, Josef Scharinger

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