Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support.
Luce is a 3D representation that unifies geometry and physically based rendering (PBR) materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for each modality. A variational autoencoder compresses this representation into a unified material‑aware latent space, which a rectified‑flow transformer generates from a single image conditioned on multi‑layer features from a pretrained image encoder. The latent decodes into relightable PBR Gaussians and an optional textured mesh with a tangent‑space normal map, achieving state‑of‑the‑art single‑image‑to‑3D generation on Toys4K and improving CLIP image‑alignment scores on a benchmark of AI‑generated images.
By Mayank Singh, Michele Stoppa, Alvise Memo, Rui Yu, Harsha Kalli, Srimanth Gunturi, Muhammad Ahmed Riaz, Behrooz Shahsavari, Waleed Abdulla, David E. Jacobs
NOFACE3D is a training‑free framework that refines fine‑scale, detail‑critical regions in 3D assets generated from a single image. It extracts a selected submesh, scales it to the generator’s input volume, and re‑encodes it into a full‑resolution latent grid, refining the region with flow‑based sampling guided by a spatially varying noise schedule. The refined region is then reintegrated, preserving surrounding geometry and appearance, and the method is evaluated on PAniC‑3D, TexVerse, and a new BigDetail benchmark, showing sharper geometry and finer texture detail.
whyItMatters: The approach improves the fidelity of small, high‑curvature structures in image‑to‑3D models without requiring additional training, addressing a key limitation in current generators.
By James Rose, Jingwen Liang, Wenchao Ma, Oren Jacob, Haomiao Jiang
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
SpatialCrafter introduces a two‑stage framework for single‑image world modeling that first generates a global 3D proxy using a Point‑anchored Sparse Structure Flow module, then refines appearance with a Generative Deferred Refiner built on a video diffusion model. The method incorporates Parallel Geometry Injection and Proxy‑Aware Corruption training to integrate the proxy without disrupting the pretrained generative manifold, and it is evaluated on a newly constructed dataset of 115K scenes. Experiments demonstrate that SpatialCrafter outperforms existing approaches, reducing long‑term drift and maintaining consistency under rapid camera motion and extreme viewpoints.
By Chuan Fang, Lingteng Qiu, Yixun Liang, Rui Chen, Kunming Luo, Zhaohua Zheng, Tongyuan Bai, Feipeng Tian, Zilong Dong, Zihan Zhou, Ping Tan
T3lescope is a generative surface reconstruction method that produces high‑fidelity 3D meshes from posed multi‑view images without per‑scene optimization. It uses a single fixed‑resolution generator in a coarse‑to‑fine cascade, where each level refines geometry within progressively finer spatial cells. Trained on cells at multiple scales, the model shares weights across all levels, allowing it to adapt the number of levels, cell scales, and locations at inference time and achieve consistent geometry across indoor, outdoor, and city‑scale scenes.
By Atsuhiro Noguchi, Tianhan Xu, Yiming Liang, Yuta Kikuchi, Masahiro Ishiyama, Shintaro Takagi, Hitoshi Murai, Eiichi Matsumoto