GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

Yan, Di; Zhang, Ruida; Lou, Zhiqiang; Manhardt, Fabian; Ji, Xiangyang; Navab, Nassir; Tombari, Federico

doi:10.48550/arxiv.2203.07918

Cited by 3 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent works explored different aspects to improve pose estimation accuracy. A category-level shape prior is found to be beneficial for pose estimation accuracy in [29] and further improved in [30], [31], [32]. DualPoseNet [33], 6D-ViT [34], ACR-Pose [35], and CPPF [36] proposed to incorporate rotation-invariant embedding, Transformer networks, Generative Adversarial Networks, and deep pointpair-feature, respectively.…”

Section: B Opaque Object Category-level Pose Estimationmentioning

confidence: 99%

“…Similar to other category-level pose estimation work [32], we fine-tune a Mask R-CNN [26] model to obtain the object's bounding box B, segmentation mask M and category label P c . Patches of ray direction R B , RGB I B and raw depth D B are extracted according to the bounding box B and serve as input to the first stage of TransNet.…”

Section: B Object Instance Detection and Segmentationmentioning

confidence: 99%

“…For both surface normal estimation and depth completion, the batch size was set to 24. For the second stage, the training hyperparameters of Pointformer and pose and scale estimation were selected following [34], [32]. The learning rate for all loss terms were kept the same during training, {λ rx , λ rz , λ ra , λ t , λ s , λ conx , λ conz } = {8, 8, 4, 8, 8, 1, 1} e −4 .…”

Section: E Transformer Feature Embeddingmentioning

confidence: 99%

“…Evaluation metrics For category-level pose estimation, this study follows [32], [31] in using 3D intersection over union (IoU) between the ground truth and estimated 3D bounding box at 25%, 50% and 75% thresholds. Additionally, 5 • 5cm, 10 • 5cm, and 10 • 10cm are used as metrics.…”

Section: E Transformer Feature Embeddingmentioning

confidence: 99%

See 3 more Smart Citations

TransNet: Category-Level Transparent Object Pose Estimation

Zhang

Opipari

Chen

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Section: B Opaque Object Category-level Pose Estimationmentioning

confidence: 99%

Section: B Object Instance Detection and Segmentationmentioning

confidence: 99%

Section: E Transformer Feature Embeddingmentioning

confidence: 99%

Section: E Transformer Feature Embeddingmentioning

confidence: 99%

See 2 more Smart Citations

TransNet: Category-Level Transparent Object Pose Estimation

Zhang

Opipari

Chen

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Recent instance-specific pose estimators [39,6,32] reconstruct the object model implicitly in the pipeline so that they are are model-free. Category-specific pose estimators [61,11,64,13,29,10,57,8,30,9,16,15] can generalize to objects in the same category and also do not require the object model. However, they are still unable to predict poses for objects in unseen categories.…”

Section: Specific Object Pose Estimatormentioning

confidence: 99%

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

Liu¹,

Wen²,

Peng³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we present a generalizable model-free 6-DoF object pose estimator called Gen6D. Existing generalizable pose estimators either need the high-quality object models or require additional depth maps or object masks in test time, which significantly limits their application scope. In contrast, our pose estimator only requires some posed images of the unseen object and is able to accurately predict poses of the object in arbitrary environments. Gen6D consists of an object detector, a viewpoint selector and a pose refiner, all of which do not require the 3D object model and can generalize to unseen objects. Experiments show that Gen6D achieves state-of-the-art results on two model-free datasets: the MOPED dataset and a new GenMOP dataset collected by us. In addition, on the LINEMOD dataset, Gen6D achieves competitive results compared with instance-specific pose estimators. Project page: https://liuyuan-pal.github.io/Gen6D/.

show abstract

AG-Net: Category-level 6D Pose Estimation Network Based on Attention Mechanism and Global Enhancement

Bowen,

Jinlong,

Suqin

et al. 2024

Preprint

View full text Add to dashboard Cite

How to effectively enhance feature extraction is a challenge faced by current 6D pose estimation methods. To address this issue, we propose a novel 6D pose estimation network based on VI-Net, shortened as AG-Net, which uses ECA block and Global enhancev module to enhance feature extraction: ECA block embeds a channel attention mechanism into the convolutional layers, replacing the fully connected layers with 1×1Conv to capture relationships between different channels and improves the performance of feature extraction. The Global enhancev module further processes the received information and enhances feature extraction by fusing global features, effectively balancing performance and speed, and better estimating the translation and size of objects. We applied the proposed AG-Net to category-level 6D pose estimation tasks and tested it on the REAL275 and CAMER25 datasets using IOU 3D intersection and n◦mcm evaluation metrics. The results showed that AG-Net outperformed current state-of-the-art methods. Our code and models are available at https://github.com/AFESDTTM/AG-Net

show abstract

GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

Cited by 3 publications

References 0 publications

TransNet: Category-Level Transparent Object Pose Estimation

TransNet: Category-Level Transparent Object Pose Estimation

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

AG-Net: Category-level 6D Pose Estimation Network Based on Attention Mechanism and Global Enhancement

Contact Info

Product

Resources

About