RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
원문 초록
General scene reconstruction refers to the task of estimating the full 3D geometry and texture of a scene containing previously unseen objects. In many practical applications such as AR/VR, autonomous navigation, and robotics, only a single view of the scene may be available, making the scene reconstruction task challenging. In this paper, we present a method for scene reconstruction by structurally breaking the problem into two steps: rendering novel views via inpainting and 2D to 3D scene lifting. Specifically, we leverage the generalization capability of large visual language models (Dalle-2) to inpaint the missing areas of scene color images rendered from different views. Next, we lift these inpainted images to 3D by predicting normals of the inpainted image and solving for the missing depth values. By predicting for normals instead of depth directly, our method allows for robustness to changes in depth distributions and scale. With rigorous quantitative evaluation, we show that our method outperforms multiple baselines while providing generalization to novel objects and scenes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation
Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images
ScaleLSD: Scalable Deep Line Segment Detection Streamlined
토론
이 논문과 연결된 포럼 글이 아직 없습니다.