Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding
원문 초록
Masked signal modeling has greatly advanced self-supervised pre-training for language and 2D images. However, it is still not fully explored in 3D scene understanding. Thus, this paper introduces Masked Shape Prediction (MSP), a new framework to conduct masked signal modeling in 3D scenes. MSP uses the essential 3D semantic cue, i.e., geometric shape, as the prediction target for masked points. The context-enhanced shape target consisting of explicit shape context and implicit deep shape feature is proposed to facilitate exploiting contextual cues in shape prediction. Meanwhile, the pre-training architecture in MSP is carefully designed to alleviate the masked shape leakage from point coordinates. Experiments on multiple 3D understanding tasks on both indoor and outdoor datasets demonstrate the effectiveness of MSP in learning good feature representations to consistently boost downstream performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Trajectory Prediction Meets Large Language Models: A Survey
OccLE: Label-Efficient 3D Semantic Occupancy Prediction
Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.