단일 이미지에서 신경망 필드와 기반 모델 특징을 추출하여 3D 장면을 인식하는 DistillNeRF
DistillNeRF는 제한된 2D 이미지 입력에서 풍부한 3D 장면 표현을 예측하기 위해 오프라인 NeRF 및 시각적 기반 모델에서 지식을 추출하는 자기 지도 학습 프레임워크입니다.
SCRREAM: A Framework and Benchmark for Annotating Dense 3D Indoor Scenes
This paper introduces SCRREAM, a novel framework for creating highly accurate and dense 3D annotations of indoor scenes, addressing limitations in existing datasets that prioritize scale over detailed geometry.
Learning-free Uplifting of 2D Visual Features to 3D Gaussian Splatting Scenes for Efficient Semantic Segmentation
This paper introduces a novel, learning-free method for uplifting 2D visual features to 3D Gaussian Splatting scenes, enabling efficient and effective semantic segmentation in 3D scenes without requiring computationally expensive optimization procedures.
SAM-Guided Masked Token Prediction for Enhanced 3D Scene Understanding via Knowledge Distillation from 2D Foundation Models
This paper introduces a novel method for improving 3D scene understanding by using a two-stage masked token prediction framework guided by SAM (Segment Anything Model) to transfer knowledge from pre-trained 2D foundation models to 3D models.
A New Method for 3D Scene Understanding Using Panoptic Segmentation within Neural Radiance Fields and Guided by Perceptual Priors
This paper proposes a novel method for 3D scene understanding that leverages 2D panoptic segmentation information within a neural radiance field framework, guided by perceptual priors, to achieve accurate and consistent 3D panoptic segmentation.
オープンボキャブラリーを用いた3Dシーングラフによるオブジェクトグラウンディング
提案手法BBQは、3Dシーングラフ表現と大規模言語モデルを組み合わせることで、複雑な自然言語クエリに基づいて3Dシーン内のオブジェクトを正確に特定することができる。
OpenSUN3D Workshop Challenge on Open-Vocabulary 3D Scene Understanding
Advancing open-vocabulary 3D scene understanding through innovative methods and challenges.
© 2024 by Linnk AI