HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion
원문 초록
We present HuGDiffusion, a generalizable 3D Gaussian splatting (3DGS) learning pipeline to achieve novel view synthesis (NVS) of human characters from single-view input images. Existing approaches typically require monocular videos or calibrated multi-view images as inputs, whose applicability could be weakened in real-world scenarios with arbitrary and/or unknown camera poses. In this paper, we aim to generate the set of 3DGS attributes via a diffusion-based framework conditioned on human priors extracted from a single image. Specifically, we begin with carefully integrated human-centric feature extraction procedures to deduce informative conditioning signals. Based on our empirical observations that jointly learning the whole 3DGS attributes is challenging to optimize, we design a multi-stage generation strategy to obtain different types of 3DGS attributes. To facilitate the training process, we investigate constructing proxy ground-truth 3D Gaussian attributes as high-quality attribute-level supervision signals. Through extensive experiments, our HuGDiffusion shows significant performance improvements over the state-of-the-art methods. Our code will be made publicly available.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision
3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
Anti-Aliased 2D Gaussian Splatting
Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
3DGEER: Exact and Efficient Volumetric Rendering with 3D Gaussians
토론
이 논문과 연결된 포럼 글이 아직 없습니다.