MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation
원문 초록
Reconstructing 3D from a single view image is a long-standing challenge. One of the popular approaches to tackle this problem is learning-based methods, but dealing with the test cases unfamiliar with training data (Out-of-distribution; OoD) introduces an additional challenge. To adapt for unseen samples in test time, we propose MeTTA, a test-time adaptation (TTA) exploiting generative prior. We design joint optimization of 3D geometry, appearance, and pose to handle OoD cases with only a single view image. However, the alignment between the reference image and the 3D shape via the estimated viewpoint could be erroneous, which leads to ambiguity. To address this ambiguity, we carefully design learnable virtual cameras and their self-calibration. In our experiments, we demonstrate that MeTTA effectively deals with OoD scenarios at failure cases of existing learning-based 3D reconstruction models and enables obtaining a realistic appearance with physically based rendering (PBR) textures.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
PanSt3R: Multi-view Consistent Panoptic Segmentation
PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wild
Bolt3D: Generating 3D Scenes in Seconds
토론
이 논문과 연결된 포럼 글이 아직 없습니다.