Signals 4 · free daily AI digest

GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space

Paper recorded by Signals 4 on 2026-09-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.CV · 计算机视觉 · first seen 2026-09-29

Abstract

Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, while maintaining world consistency across viewpoints. Existing geometry-based methods preserve observed scene structure but often struggle to complete unseen regions, whereas video generative models offer rich appearance priors but accumulate inconsistenc

Read on arXiv →

#3 most recent of 342 cs.CV papers we have recorded · ↑ newer: InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentr · ↓ older: FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References
Cite this page: GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space: the #3 most recent of 342 cs.CV papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/geoverse-world-consistent-novel-view-synthesis-in-geometric-latent-space.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions