VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis

arXiv 2026 19 method

TLDR

VGGT-Diff routes geometry latents from VGGT-Ω into a video diffusion model for sparse-view novel view synthesis, improving interpolation and extrapolation.

Reasoning

The paper presents a strong integration of geometric reconstruction with generative diffusion for novel view synthesis, with experiments showing competitive results. However, it does not position itself as a world model or focus on world dynamics, limiting relevance to those keywords.

Read-first score

Read-first score 19, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 5.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment

Topical relevance 25%

7.1

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 62.

Keyword Scores

video world model

world model

generative world model

world dynamics prediction

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper