효율적인 3차원 개체 분할을 위한 개체 위치 인코딩과 이중 노이즈 제거 작업들 (Instance Position Encoding and Dual Denoising Tasks for Efficient 3D Instance Segmentation)

서지정보

· 발행기관 : 한국멀티미디어학회
· 수록지 정보 : 멀티미디어학회논문지 / 27권 / 4호 / 490 ~ 504페이지
· 저자명 : 송성호, 김인철

초록

As a 3D scene understanding task, 3D point cloud instance segmentation is to predict simultaneously both their 3D mask and class label of individual object instances included in a given point cloud. There are some important issues to design an efficient Transformer-based 3D point cloud instance segmenta tion model: instance query position encoding, instance mask and query refinement, auxiliary task learning. In order to overcome the limitations of existing models, this paper proposes a novel Transfor mer-based model, DP3DIS, which contains some distinct solutions such as position encoding based on 3D bounding box of an instance, a new masked modulate cross attention with consideration of instance size or volume, denoising auxiliary tasks applied for both instance query and instance attention mask.
In this paper, we demonstrate the superiority of the proposed model Through quantitative and qualitative experiments conducted on ScanNet v2, we showed the superiority of the proposed DP3DIS, model.

영어초록

As a 3D scene understanding task, 3D point cloud instance segmentation is to predict simultaneously both their 3D mask and class label of individual object instances included in a given point cloud. There are some important issues to design an efficient Transformer-based 3D point cloud instance segmenta tion model: instance query position encoding, instance mask and query refinement, auxiliary task learning. In order to overcome the limitations of existing models, this paper proposes a novel Transfor mer-based model, DP3DIS, which contains some distinct solutions such as position encoding based on 3D bounding box of an instance, a new masked modulate cross attention with consideration of instance size or volume, denoising auxiliary tasks applied for both instance query and instance attention mask.
In this paper, we demonstrate the superiority of the proposed model Through quantitative and qualitative experiments conducted on ScanNet v2, we showed the superiority of the proposed DP3DIS, model.

참고자료

· 없음