arXiv:1911.01911
공식 코드 · Papers with Code
BlenderProc
원문 초록
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose estimation and many others. A key feature of our extension of blender is the simple to use modular pipeline, which was designed to be easily extendable. By offering standard modules, which cover a variety of scenarios, we provide a starting point on which new modules can be created.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Accurate and efficient zero-shot 6D pose estimation with frozen foundation models
PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation
PPR-Net:Point-wise Pose Regression Network for Instance Segmentation and 6D Pose Estimation in Bin-picking Scenarios
No time to train! Training-Free Reference-Based Instance Segmentation
NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.