Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild
원문 초록
Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics. While recent neural implicit modeling methods show promising results on synthetic or dense data, they perform poorly on sparse and noisy real-world data. We discover that the limitations of a popular neural implicit model are due to lack of robust shape priors and lack of proper regularization. In this work, we demonstrate highquality in-the-wild shape reconstruction using: (i) a deep encoder as a robust-initializer of the shape latent-code; (ii) regularized test-time optimization of the latent-code; (iii) a deep discriminator as a learned high-dimensional shape prior; (iv) a novel curriculum learning strategy that allows the model to learn shape priors on synthetic data and smoothly transfer them to sparse real world data. Our approach better captures the global structure, performs well on occluded and sparse observations, and registers well with the ground-truth shape. We demonstrate superior performance over state-of-the-art 3D object reconstruction methods on two real-world datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction
View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction
TripoSR: Fast 3D Object Reconstruction from a Single Image
토론
이 논문과 연결된 포럼 글이 아직 없습니다.