[3D Vision] Transformer based 3DSS
1.Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approachespredominantly rely on specialized voting mechanismsfollowed by carefully designed geometric cluster
2023년 9월 15일
2.Mask-Attention-Free Transformer for 3D Instance Segmentation
🚀 Motivation Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically,
2023년 9월 18일
3.[Mask2Former] Masked-attention Mask Transformer for Universal Image Segmentation (CVPR 2022)
Base of Mask3D architecture
2023년 9월 25일
4.[DETR] End-to-End Object Detection with Transformers (ECCV 2020)
Authors: Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey ZagoruykoDETR is a new method that views o
2023년 9월 27일
5.[MaskFormer] 논문 정리
Per-Pixel Classification vs Mask Classification Per-pixel classification 모든 pixel들에 대해 K개의 카테고리들에 속할 확률 분포를 예측한다. 만약, $H \times W$ image가 있다고 한다면, $\
2023년 10월 26일