Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
원문 초록
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D shape detail that is hidden behind several layers of occlusion. We provide a novel view merging method for combining view dependent information (Eg. MLH descriptors) from multiple views. Because of the ability of using 2D CNNs, our method is highly memory efficient in terms of input resolution compared to the voxel based input. Together with MLH descriptors and our multi view merging, we achieve the state-of-the-art result in classification on ModelNet dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
DC3DO: Diffusion Classifier for 3D Objects
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors
Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid Approach
토론
이 논문과 연결된 포럼 글이 아직 없습니다.