Signals 4 · free daily AI digest

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper recorded by Signals 4 on 2026-09-21 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.CV · 计算机视觉 · first seen 2026-09-22

Abstract

We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generators can produce photorealistic frames without preserving a consistent 3D scene. We argue that this is not only a modeling problem but also a representation problem: generators typically evolve appearance-centric latents, while perception models recover geometry in a semantically ri

Read on arXiv →

#2 most recent of 270 cs.CV papers we have recorded · ↑ newer: VideoGen-Agent: Reinforcing Video Generation Agents · ↓ older: Anatomy-Decomposed Chest Computed Tomography (CT) Projections as Scala
Cite this page: GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation: the #2 most recent of 270 cs.CV papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/gae-learning-a-geometry-native-latent-space-for-3d-consistent-world-generation.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