paper-with-me

Papers

OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction

2024-03-08 · Ji Zhang, Yiran Ding, Zixin Liu

3D occupancy prediction based on multi-sensor fusion,crucial for a reliable autonomous driving system, enables fine-grained understanding of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D image features. However, depth estimation is an ill-posed problem, hindering the accuracy and robustness of these methods. Furthermore, fine-grained occupancy prediction demands extensive computational resources. To address these issues, we propose OccFusion, a depth estimation free multi-modal fusion framework. Additionally, we introduce a generalizable active training method and an active decoder that can be applied to any occupancy prediction model, with the potential to enhance their performance. Experiments conducted on nuScenes-Occupancy and nuScenes-Occ3D demonstrate our framework's superior performance. Detailed ablation studies highlight the effectiveness of each proposed method.

📄 PDF Abstract BibTeX arXiv:2403.05329

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDecoderDepth EstimationPredictionSensor Fusion

Similar Papers 제목 키워드 기반

OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction

2024-03-03 · Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall

A comprehensive understanding of 3D scenes is crucial in autonomous vehicles (AVs), and recent models for 3D semantic occupancy prediction have successfully addressed the challenge of describing real-world objects with v…

3D Semantic Occupancy PredictionAutonomous DrivingAutonomous VehiclesPrediction+1

OccFusion: Rendering Occluded Humans with Generative Diffusion Priors

2024-06-29 · Adam Sun, Tiange Xiang, Scott Delp, Li Fei-Fei 외

Most existing human rendering methods require every part of the human to be fully visible throughout the input video. However, this assumption does not hold in real-life settings where obstructions are common, resulting …

AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs

2026-05-04 · Simon Dorer, Martin Büchner, Nick Heppert, Abhinav Valada arxiv

Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces…

Monocular Depth Estimation

Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

2022-03-09 · Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environment…

Depth Estimationobject-detectionObject DetectionRGB-D Salient Object Detection+1

Efficient Multi-Frequency Phase Unwrapping using Kernel Density Estimation

2016-08-18 · Felix Järemo Lawin, Per-Erik Forssén, Hannes Ovrén

In this paper we introduce an efficient method to unwrap multi-frequency phase estimates for time-of-flight ranging. The algorithm generates multiple depth hypotheses and uses a spatial kernel density estimate (KDE) to r…

Density Estimationvalid