16 papers
MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation
Junkai Lin, Tianhao Zhao, Hang Long +10
Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token costs, or continuous flow mode…
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
Hang Long, Tianhao Zhao, Junkai Lin +8
Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model ver…
Do Image Editing Models Understand Lighting?
Tim Küchler, Johann-Friedrich Feiden, Matthias Nießner +1
While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these systems possess an intrinsic knowledg…
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
Bartłomiej Baranowski, Dave Zhenyu Chen, Matthias Nießner
Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spat…
TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
Haoxuan Li, Ziya Erkoç, Daniele Sirigatti +4
We present TriFlow, a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry conditions such as signed distance fie…
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Katharina Schmid, Nicolas von Lützow, Jozef Hladký +2
We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene…
DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing
Jinxin Ai, Matthias Nießner, Ziya Erkoç
While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the…
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
Ziya Erkoç, Angela Dai, Matthias Nießner
Given the remarkable ability of 2D foundation image models to generate high-fidelity outputs, we investigate a fundamental question: do 2D foundation image models inherently posses…
World Reconstruction From Inconsistent Views
Lukas Höllein, Matthias Nießner
Video diffusion models generate high-quality and diverse worlds; however, individual frames often lack 3D consistency across the output sequence, which makes the reconstruction of…
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
Tianhao Zhao, Youjia Zhang, Hang Long +7
In this paper, we introduce LATO, a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes. LATO represents a me…
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
Nicolas von Lützow, Barbara Rössle, Katharina Schmid +1
Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a t…
MeshRipple: Structured Autoregressive Generation of Artist-Meshes
Junkai Lin, Hang Long, Huipeng Guo +8
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference…
Zero-shot Inexact CAD Model Alignment from a Single Image
Pattaramanee Arsomngern, Sasikarn Khwanmuang, Matthias Nießner +1
One practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image. Existin…
PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors
Yujin Chen, Yinyu Nie, Benjamin Ummenhofer +3
We present PBR-SR, a novel method for physically based rendering (PBR) texture super resolution (SR). It outputs high-resolution, high-quality PBR textures from low-resolution (LR)…
MTGS: Multi-Traversal Gaussian Splatting
Tianyu Li, Yihang Qiu, Zhenhua Wu +4
Multi-traversal data, commonly collected through daily commutes or by self-driving fleets, provides multiple viewpoints for scene reconstruction within a road block. This data offe…
LinPrim: Linear Primitives for Differentiable Volumetric Rendering
Nicolas von Lützow, Matthias Nießner
Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views…