Pith. sign in

SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Sparse Multi-view Images can be Learned to predict explicit radiance fields via Generalizable Gaussian Splatting approaches, which can achieve wider application prospects in real-life when ground-truth camera parameters are not required as inputs. In this paper, a novel generalizable Gaussian Splatting method, SmileSplat, is proposed to reconstruct pixel-aligned Gaussian surfels for diverse scenarios only requiring unconstrained sparse multi-view images. First, Gaussian surfels are predicted based on the multi-head Gaussian regression decoder, which can are represented with less degree-of-freedom but have better multi-view consistency. Furthermore, the normal vectors of Gaussian surfel are enhanced based on high-quality of normal priors. Second, the Gaussians and camera parameters (both extrinsic and intrinsic) are optimized to obtain high-quality Gaussian radiance fields for novel view synthesis tasks based on the proposed Bundle-Adjusting Gaussian Splatting module. Extensive experiments on novel view rendering and depth map prediction tasks are conducted on public datasets, demonstrating that the proposed method achieves state-of-the-art performance in various 3D vision tasks. More information can be found on our project page (https://yanyan-li.github.io/project/gs/smilesplat)

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2024 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

cs.CV · 2024-12-05 · reject · novelty 3.0

A dynamic Gaussian rendering method that wraps a third-order time polynomial around an SC-GS style skeleton and reports higher PSNR, though the 'infinite Taylor' framing is a fitted residual network.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learnable Infinite Taylor Gaussian for Dynamic View Rendering cs.CV · 2024-12-05 · reject · none · ref 20 · internal anchor

    A dynamic Gaussian rendering method that wraps a third-order time polynomial around an SC-GS style skeleton and reports higher PSNR, though the 'infinite Taylor' framing is a fitted residual network.