Diffgs: Functional gaussian splatting diffusion

J Zhou, W Zhang, YS Liu - Advances in Neural Information …, 2025 - proceedings.neurips.cc
Abstract 3D Gaussian Splatting (3DGS) has shown convincing performance in rendering
speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its …

Learning unsigned distance functions from multi-view images with volume rendering priors

W Zhang, K Shi, YS Liu, Z Han - European Conference on Computer …, 2024 - Springer
Unsigned distance functions (UDFs) have been a vital representation for open surfaces.
With different differentiable renderers, current methods are able to train neural networks to …

Neural signed distance function inference through splatting 3d gaussians pulled on zero-level set

W Zhang, YS Liu, Z Han - arxiv preprint arxiv:2410.14189, 2024 - arxiv.org
It is vital to infer a signed distance function (SDF) in multi-view based surface reconstruction.
3D Gaussian splatting (3DGS) provides a novel perspective for volume rendering, and …

NeuralTPS: Learning signed distance functions without priors from single sparse point clouds

C Chen, YS Liu, Z Han - IEEE Transactions on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Surface reconstruction for point clouds is one of the important tasks in 3D computer vision.
The latest methods rely on generalizing the priors learned from large scale supervision …

Inferring 3D occupancy fields through implicit reasoning on silhouette images

B Ma, YS Liu, M Zwicker, Z Han - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Implicit 3D representations have shown great promise in deep learning-based 3D
reconstruction. With differentiable renderers, current methods are able to learn implicit …