GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hao, Zhang, Dingwen, Dai, Yalun, Liu, Nian, Cheng, Lechao, Li, Jingfeng, Wang, Jingdong, Han, Junwei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914742903242752
author Li, Hao
Zhang, Dingwen
Dai, Yalun
Liu, Nian
Cheng, Lechao
Li, Jingfeng
Wang, Jingdong
Han, Junwei
author_facet Li, Hao
Zhang, Dingwen
Dai, Yalun
Liu, Nian
Cheng, Lechao
Li, Jingfeng
Wang, Jingdong
Han, Junwei
contents Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, we conduct experimental comparisons under two perception tasks (\textit{i.e.} semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94\%, 11.76\%, and 8.47\% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11863
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Li, Hao
Zhang, Dingwen
Dai, Yalun
Liu, Nian
Cheng, Lechao
Li, Jingfeng
Wang, Jingdong
Han, Junwei
Computer Vision and Pattern Recognition
Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, we conduct experimental comparisons under two perception tasks (\textit{i.e.} semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94\%, 11.76\%, and 8.47\% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively.
title GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.11863