Neural 3D Scene Reconstruction from Multiple 2D Images without 3D Supervision
원문 초록
Neural 3D scene reconstruction methods have achieved impressive performance when reconstructing complex geometry and low-textured regions in indoor scenes. However, these methods heavily rely on 3D data which is costly and time-consuming to obtain in real world. In this paper, we propose a novel neural reconstruction method that reconstructs scenes using sparse depth under the plane constraints without 3D supervision. We introduce a signed distance function field, a color field, and a probability field to represent a scene. We optimize these fields to reconstruct the scene by using differentiable ray marching with accessible 2D images as supervision. We improve the reconstruction quality of complex geometry scene regions with sparse depth obtained by using the geometric constraints. The geometric constraints project 3D points on the surface to similar-looking regions with similar features in different 2D images. We impose the plane constraints to make large planes parallel or vertical to the indoor floor. Both two constraints help reconstruct accurate and smooth geometry structures of the scene. Without 3D supervision, our method achieves competitive performance compared with existing methods that use 3D supervision on the ScanNet dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
WeatherEdit: Controllable Weather Editing with 4D Gaussian Field
RealEngine: Simulating Autonomous Driving in Realistic Context
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.