paper-with-me

홈 › Papers

ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion

2023-01-01 · ICCV 2023 1 · Qi Cai, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei

Recent progress on multi-modal 3D object detection has featured BEV (Bird-Eye-View) based fusion, which effectively unifies both LiDAR point clouds and camera images in a shared BEV space. Nevertheless, it is not trivial to perform camera-to-BEV transformation due to the inherently ambiguous depth estimation of each pixel, resulting in spatial misalignment between these two multi-modal features. Moreover, such transformation also inevitably leads to projection distortion of camera image features in BEV space. In this paper, we propose a novel Object-centric Fusion (ObjectFusion) paradigm, which completely gets rid of camera-to-BEV transformation during fusion to align object-centric features across different modalities for 3D object detection. ObjectFusion first learns three kinds of modality-specific feature maps (i.e., voxel, BEV, and image features) from LiDAR point clouds and its BEV projections, camera images. Then a set of 3D object proposals are produced from the BEV features via a heatmap-based proposal generator. Next, the 3D object proposals are reprojected back to voxel, BEV, and image spaces. We leverage voxel and RoI pooling to generate spatially aligned object-centric features for each modality. All the object-centric features of three modalities are further fused at object level, which is finally fed into the detection heads. Extensive experiments on nuScenes dataset demonstrate the superiority of our ObjectFusion, by achieving 69.8% mAP on nuScenes validation set and improving BEVFusion by 1.3%.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionDepth EstimationObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

RSFusionDet: Underwater RGB-Sonar Multimodal Object Detection

2026-08-26 · Zhuoyan Liu, Yihan Wang, Bo Wang, Bing Wang 외 arxiv

Underwater unimodal object detection faces many challenges in sensor imaging, such as optical images limited by underwater noise and visible distance, and sonar images limited by less object structural information. While…

Object Detection

Multimodal Object Detection in Remote Sensing

2023-07-13 · Abdelbadie Belmouhcine, Jean-Christophe Burnel, Luc Courtrai, Minh-Tan Pham 외

Object detection in remote sensing is a crucial computer vision task that has seen significant advancements with deep learning techniques. However, most existing works in this area focus on the use of generic object dete…

Objectobject-detectionObject DetectionSurvey

Multimodal Object Detection via Probabilistic a priori Information Integration

2024-05-24 · Hafsa El Hafyani, Bastien Pasdeloup, Camille Yver, Pierre Romenteau

Multimodal object detection has shown promise in remote sensing. However, multimodal data frequently encounter the problem of low-quality, wherein the modalities lack strict cell-to-cell alignment, leading to mismatch be…

Objectobject-detectionObject Detection

LMM-Det: Make Large Multimodal Models Excel in Object Detection

2025-07-24 · Jincheng Li, Chunyu Xie, Ji Ao, Dawei Leng 외 arxiv

Large multimodal models (LMMs) have garnered wide-spread attention and interest within the artificial intelligence research and industrial communities, owing to their remarkable capability in multimodal understanding, re…

Visual Question AnsweringVisual GroundingObject DetectionImage Captioning

Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection

2023-08-30 · Yifan Xu, Mengdan Zhang, Xiaoshan Yang, Changsheng Xu

In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint r…

Knowledge DistillationLanguage ModelingLanguage ModellingMasked Language Modeling+5