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.
By Yizhao Wang, Jingbo Wang, Guantao Zhang
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...
By Han Liang, Sibo Wu, Anpei Chen, R\"udiger Westermann
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...
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.
By Yizhao Wang
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.
By Jiahao Lu, Minghao Yin, Wenbo Hu, Hengyu Liu, Wang Zhao, Sai-Kit Yeung, Ying Shan, Yuan Liu
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...
By Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang, Yi Wu, Linqing Zhao, Haibin Yan
arXiv:2609.23182v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric co...
By Si-Yu Lu, Yung-Yao Chen, Yi Jan Chen, Shang-Lin Li, Ching-Chan Liao, Wen-Huang Cheng
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. By representing only occupied voxels in a compact latent space and training a masked autoregressive transformer with photometric supervision via differentiable 3D Gaussian Splatting, the method predicts missing latent tokens and spatial support, enabling efficient and spatially consistent generation of unseen regions. Experiments on synthetic indoor scenes and RealEstate10k demonstrate higher novel‑view quality and real‑world applicability compared to prior work.
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. It learns a compact voxel‑aligned latent space using photometric supervision via differentiable 3D Gaussian Splatting, and employs a masked autoregressive transformer to predict missing voxel occupancy and latent tokens. Experiments on synthetic indoor scenes and RealEstate10k show that SPAR3S achieves higher novel‑view quality than prior methods and generalizes to real‑world data.
By Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel, Wonjune Cho, Bardienus Pieter Duisterhof, Vincent Leroy, Jerome Revaud
arXiv:2610.07958v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
By Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
arXiv:2511.21265v2 Announce Type: replace
Abstract: Learning-based image matching critically depends on large-scale, diverse, and geometrically accurate training data. 3D Gaussian Splatting (3DGS) en...
By Juncheng Chen, Chao Xu, Yanjun Cao
arXiv:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.
By Zhenjia Li, Jinrang Jia, Yifeng Shi