Skip to content
Book

Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance

Oct 2026 · 0 citations · 9 references
Computer Science

TL;DR

A 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scene reconstruction from only six cameras with wide baselines, ranking first overall in the Sparse-View Track.

Abstract

We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scene reconstruction from only six cameras with wide baselines. To achieve robust dynamic reconstruction under such sparse views, our framework integrates three components. (1) Region-adaptive spatial priors: We use foreground masks to guide Gaussian initialization and mask voting to control densification separately for the dynamic foreground and static background. Background geometry is regularized using monocular depth aligned to metric scale. (2) Motion-consistent temporal priors: We provide supervision at intermediate times through frame interpolation and constrain projected Gaussian motion with estimated optical flow. (3) Generative assistance: We place virtual cameras in the widest angular gaps and restore their rendered images using a diffusion-based model conditioned on camera poses. The restored images are iteratively incorporated into training as pseudo-supervision. On the validation set, our framework improves full-frame PSNR from 25.60 dB for the baseline to 29.75 dB. On the official test benchmark, it achieves 30.04 dB full-frame PSNR and 27.88 dB foreground PSNR, ranking first overall in the Sparse-View Track.

View source

Similar papers

Sep 2026

GAPS: Generative Active Pseudo-view Selection for Sparse-View 3D Gaussian Splatting

An alternating optimization framework that uses a pre-trained image diffusion model to generate geometrically consistent pseudo-views for additional 3DGS supervision and introduces Generative Active Pseudo-view Selection (GAPS) to balance reconstruction informativeness and generative reliability when choosing target vi...

Hong-Fei Zhu, Hao-Chen Deng, Si-Tao Zhang et al. · 0 citations
Preprint Aug 2026

FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors

This work presents FixAnything, a single model for fixing a wide range of rendering artifacts by repurposing a pretrained video generative model, leveraging its implicit multi-view priors with only minimal modification and lightweight finetuning.

Khiem Vuong, D. Ramanan, Srinivasa G. Narasimhan · 1 citation
Sep 2026

D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction

D3GS is proposed, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance and injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation.

Yun-Qi Gao, Zhan-Feng Liao, Han-Zhang Tu et al. · 0 citations
Open access Sep 2026

GeoSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Geometry-Aware Priors

This work introduces a geometry-aware cost volume that injects relative pose distance, view-dependent ray angle, and spatial validity masks into dense depth matching, enabling the network to jointly reason about photometric consistency, triangulation reliability, and visibility.

Yue-Sheng Hao, Guang-Mang Cui, Ye-Cheng Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.