CompNVS: Novel View Synthesis with Scene Completion
원문 초록
We introduce a scalable framework for novel view synthesis from RGB-D images with largely incomplete scene coverage. While generative neural approaches have demonstrated spectacular results on 2D images, they have not yet achieved similar photorealistic results in combination with scene completion where a spatial 3D scene understanding is essential. To this end, we propose a generative pipeline performing on a sparse grid-based neural scene representation to complete unobserved scene parts via a learned distribution of scenes in a 2.5D-3D-2.5D manner. We process encoded image features in 3D space with a geometry completion network and a subsequent texture inpainting network to extrapolate the missing area. Photorealistic image sequences can be finally obtained via consistency-relevant differentiable rendering. Comprehensive experiments show that the graphical outputs of our method outperform the state of the art, especially within unobserved scene parts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View Synthesis
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.