DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
원문 초록
We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process, obviating the need for 3D data. However, this process is often inefficient due to the need for iterative updates of costly 3D representations, such as neural radiance fields, either through individual view edits or score distillation sampling. A major disadvantage of this approach is the slow convergence caused by aggregating inconsistent information across views, as the guidance from 2D models is not multi-view consistent. We thus introduce the Direct Gaussian Editor (DGE), a method that addresses these issues in two stages. First, we modify a given high-quality image editor like InstructPix2Pix to be multi-view consistent. To do so, we propose a training-free approach that integrates cues from the 3D geometry of the underlying scene. Second, given a multi-view consistent edited sequence of images, we directly and efficiently optimize the 3D representation, which is based on 3D Gaussian Splatting. Because it avoids incremental and iterative edits, DGE is significantly more accurate and efficient than existing approaches and offers additional benefits, such as enabling selective editing of parts of the scene.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
Dense 3D Displacement Estimation for Landslide Monitoring via Fusion of TLS Point Clouds and Embedded RGB Images
ScaleLSD: Scalable Deep Line Segment Detection Streamlined
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos
토론
이 논문과 연결된 포럼 글이 아직 없습니다.