arXiv Computer Vision
TriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 24
Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows
The paper introduces a fusion‑aware hierarchical Gaussian patch representation that enables direct class‑guided generation of 3D Gaussian Splatting (3DGS) objects. By decomposing irregular Gaussian sets into canonical local patches and encoding them as structured tokens, the method fuses global class semantics with patch‑level geometry, appearance, spatial correspondence, and rendering‑sensitive cues. A structure‑aware rectified flow model, conditioned on patch positions and coupled with global‑local velocity prediction and density‑aware weighting, produces class‑conditioned 3DGS objects within seconds, achieving more coherent geometry, sharper local details, and better multi‑view consistency than baseline models.
arXiv Computer Vision
Oct 15
CoTL: Compact Token Learning for 3D Scene Representation
arXiv:2610.18446v2 Announce Type: replace Abstract: We present CoTL, a framework that learns a compact set of tokens that preserves scene geometry and appearance from unposed multi-view images. Our e...
Hugging Face Trending Papers
Oct 14
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally raises a complement...
arXiv Computer Vision
Sep 24
Visibility-Guided Structured Measure Flow for Class-Conditioned 3D Gaussian Generation
The paper introduces VISTA-GS, a visibility‑guided structured measure flow framework for generating class‑conditioned 3D Gaussian Splatting (3DGS) objects. It treats a 3DGS object as a structured Gaussian measure weighted by opacity, anisotropic covariance, and multi‑view visibility, and employs a visibility‑aware VAE to learn permutation‑invariant, variable‑size, rendering‑aware latent representations. The method includes a renderer‑consistent measure flow and structure‑preserving patch transport, achieving 60–72% improvements over the strongest baseline on the VISTA‑Obj30 dataset in geometry, appearance, view‑consistency, and speed.
arXiv Computer Vision
Sep 22
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
The paper introduces the Geometry‑Native Autoencoder (GAE), a compact latent space that can be decoded into appearance, depth, camera parameters, and point maps, enabling 3D‑consistent world generation. By reparameterizing a geometry foundation model’s features, GAE replaces traditional appearance‑centric latents and improves visual quality and 3D coherence, achieving significant reductions in FVD and camera‑trajectory error on benchmark datasets. The work demonstrates that a geometry‑native latent space can serve as a shared interface between perception and generation models.
arXiv Computer Vision
Oct 15
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
arXiv:2610.19708v1 Announce Type: new Abstract: Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene r...