ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstruction
원문 초록
Single-image 3D human reconstruction aims to reconstruct the 3D textured surface of the human body given a single image. While implicit function-based methods recently achieved reasonable reconstruction performance, they still bear limitations showing degraded quality in both surface geometry and texture from an unobserved view. In response, to generate a realistic textured surface, we propose ReFu, a coarse-to-fine approach that refines the projected backside view image and fuses the refined image to predict the final human body. To suppress the diffused occupancy that causes noise in projection images and reconstructed meshes, we propose to train occupancy probability by simultaneously utilizing 2D and 3D supervisions with occupancy-based volume rendering. We also introduce a refinement architecture that generates detail-preserving backside-view images with front-to-back warping. Extensive experiments demonstrate that our method achieves state-of-the-art performance in 3D human reconstruction from a single image, showing enhanced geometry and texture quality from an unobserved view.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
HumanGif: Single-View Human Diffusion with Generative Prior
Efficient Neural Implicit Representation for 3D Human Reconstruction
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
토론
이 논문과 연결된 포럼 글이 아직 없습니다.