A survey on 3d gaussian splatting

G Chen, W Wang - arxiv preprint arxiv:2401.03890, 2024‏ - arxiv.org
3D Gaussian splatting (GS) has recently emerged as a transformative technique in the realm
of explicit radiance field and computer graphics. This innovative approach, characterized by …

Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images

Y Chen, H Xu, C Zheng, B Zhuang, M Pollefeys… - … on Computer Vision, 2024‏ - Springer
We introduce MVSplat, an efficient model that, given sparse multi-view images as input,
predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we …

Mvsplat360: Feed-forward 360 scene synthesis from sparse views

Y Chen, C Zheng, H Xu, B Zhuang… - Advances in …, 2025‏ - proceedings.neurips.cc
We introduce MVSplat360, a feed-forward approach for 360 novel view synthesis (NVS) of
diverse real-world scenes, using only sparse observations. This setting is inherently ill …

FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes

Y Wang, T Huang, H Chen… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Abstract Empowering 3D Gaussian Splatting with generalization ability is appealing.
However, existing generalizable 3D Gaussian Splatting methods are largely confined to …

Flowmap: High-quality camera poses, intrinsics, and depth via gradient descent

C Smith, D Charatan, A Tewari, V Sitzmann - arxiv preprint arxiv …, 2024‏ - arxiv.org
This paper introduces FlowMap, an end-to-end differentiable method that solves for precise
camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our …

Splatt3r: Zero-shot gaussian splatting from uncalibrated image pairs

B Smart, C Zheng, I Laina, VA Prisacariu - arxiv preprint arxiv:2408.13912, 2024‏ - arxiv.org
In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D
reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural …

L3dg: Latent 3d gaussian diffusion

B Roessle, N Müller, L Porzi, S Rota Bulò… - SIGGRAPH Asia 2024 …, 2024‏ - dl.acm.org
We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a
latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling …

Depthsplat: Connecting gaussian splatting and depth

H Xu, S Peng, F Wang, H Blum, D Barath… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Gaussian splatting and single/multi-view depth estimation are typically studied in isolation.
In this paper, we present DepthSplat to connect Gaussian splatting and depth estimation …

AIM 2024 sparse neural rendering challenge: Dataset and benchmark

M Nazarczuk, T Tanay, S Catley-Chandar… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent developments in differentiable and neural rendering have made impressive
breakthroughs in a variety of 2D and 3D tasks, eg novel view synthesis, 3D reconstruction …

Gghead: Fast and generalizable 3d gaussian heads

T Kirschstein, S Giebenhain, J Tang… - SIGGRAPH Asia 2024 …, 2024‏ - dl.acm.org
Learning 3D head priors from large 2D image collections is an important step towards high-
quality 3D-aware human modeling. A core requirement is an efficient architecture that scales …