Recent progress in image and video synthesis has inspired their use in advancing 3D scene generation. However, we observe that text-to-image and -video approaches struggle to maintain scene- and object-level consistency beyond a limited environment scale without a persistent, explicit geometric representation. We thus present a geometry-first approach that decouples this complex problem of large-scale 3D scene synthesis into its structural composition, represented as a mesh scaffold, and realistic appearance synthesis, which leverages powerful image synthesis models conditioned on the mesh scaffold. From an input text description, we first construct a mesh capturing the environment's geometry (walls, floors, etc.), and then use image synthesis, segmentation and object reconstruction to populate the mesh structure with objects in realistic layouts. This mesh scaffold is then rendered to condition image synthesis, providing a structural backbone for consistent appearance generation. This enables scalable, arbitrarily-sized 3D scenes of high object richness and diversity, combining robust 3D consistency with photorealistic detail. We believe this marks a significant step toward generating truly environment-scale, immersive 3D worlds.
MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
Tsinghua University（清华大学）；Shanghai Jiaotong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）；VAST（VAST机构）；The Chinese University of Hong Kong（香港中文大学）
Latent diffusion models for image generation have crossed a quality threshold which enabled them to achieve mass adoption. Recently, a series of works have made advancements towards replicating this success in the 3D domain, introducing techniques such as point cloud VAE, triplane representation, neural implicit surfaces and differentiable rendering based training. We take another step along this direction, combining these developments in a two-step pipeline consisting of 1) a triplane VAE which can learn latent representations of textured meshes and 2) a conditional diffusion model which gene…
Current 6D object pose methods consist of deep CNN models fully optimized for a single object but with its architecture standardized among objects with different shapes. In contrast to previous works, we explicitly exploit each object's distinct topological information i.e. 3D dense meshes in the pose estimation model, with an automated process and prior to any post-processing refinement stage. In order to achieve this, we propose a learning framework in which a Graph Convolutional Neural Network reconstructs a pose conditioned 3D mesh of the object. A robust estimation of the allocentric orie…
While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such models. In this work, we bridge this gap by leveraging recent advances in differentiable rendering. We design a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations…
Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
Department of Electronic Engineering, Sogang University（电子工程系，ソガン大学）；Department of Electrical and Electronics Engineering, Pusan National University（电气电子工程系，釜山国立大学）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立高等物理、数学与信息学院）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；ETH Zürich（苏黎世联邦理工学院）
Three-dimensional human body models are widely used in the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scans and thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shapes. To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation f…
State estimation is one of the greatest challenges for cloth manipulation due to cloth's high dimensionality and self-occlusion. Prior works propose to identify the full state of crumpled clothes by training a mesh reconstruction model in simulation. However, such models are prone to suffer from a sim-to-real gap due to differences between cloth simulation and the real world. In this work, we propose a self-supervised method to finetune a mesh reconstruction model in the real world. Since the full mesh of crumpled cloth is difficult to obtain in the real world, we design a special data collect…
Modeling 3D Surface Manifolds with a Locally Conditioned Atlas
Faculty of Mathematics and Computer Science, Jagiellonian University（雅盖隆大学数学与计算机科学学院）；IDEAS NCBR；Wroclaw University of Science and Technology（弗罗茨瓦夫理工大学）；Warsaw University of Technology（华沙理工大学）
Zhejiang University（浙江大学）；Shanghai Innovation Institute（上海创新研究院）；Westlake University（西湖大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Fudan University（复旦大学）
Tsinghua University（清华大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院（AIR））；University of Chinese Academy of Sciences（中国科学院大学）
Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse object occlusions in scenarios such as autonomous driving. Recent advances show that implicit representation learning can be leveraged for continuous scene completion and achieved through physical constraints like Eikonal equations. However, former Eikonal completion methods only demonstrate results on watertight meshes at a scale of tens of meshes. None of them are successfully done for non-watertight LiDAR point clouds …
Facebook AI Research（Facebook人工智能研究院）；University of Michigan（密歇根大学）；Carnegie Mellon University（卡内基梅隆大学）
We present an approach to infer the 3D shape, texture, and camera pose for an object from a single RGB image, using only category-level image collections with foreground masks as supervision. We represent the shape as an image-conditioned implicit function that transforms the surface of a sphere to that of the predicted mesh, while additionally predicting the corresponding texture. To derive supervisory signal for learning, we enforce that: a) our predictions when rendered should explain the available image evidence, and b) the inferred 3D structure should be geometrically consistent with lear…
Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；KOKONI3D, Moxin (Huzhou) Technology Co., LTD（墨芯（湖州）科技有限公司）；School of Software Technology, Zhejiang University（浙江大学软件学院）；School of Information Engineering, Huzhou University（湖州师范学院信息工程学院）
Facebook AI Research (FAIR)（脸书人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）
We present Worldsheet, a method for novel view synthesis using just a single RGB image as input. The main insight is that simply shrink-wrapping a planar mesh sheet onto the input image, consistent with the learned intermediate depth, captures underlying geometry sufficient to generate photorealistic unseen views with large viewpoint changes. To operationalize this, we propose a novel differentiable texture sampler that allows our wrapped mesh sheet to be textured and rendered differentiably into an image from a target viewpoint. Our approach is category-agnostic, end-to-end trainable without …
Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate novel and high-quality volumetric meshes. Unlike the previous 3D generative model for point cloud, voxel, and implicit surface, the volumetric mesh representation is a ready-to-use representation in industry with details on both the surface and interior. Generating this such highly-structured data thus brings a significant challenge. We first propose a diffusion-based generative model to tackle this problem by gener…
Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；College of AI, Tsinghua University（清华大学人工智能学院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Text-Conditioned Multi-Expert Regression Framework for Fully Automated Multi-Abutment Design
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；AI Research Center for Medical Image Analysis and Diagnosis, Shenzhen University（深圳大学医学图像分析与诊断人工智能研究中心）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；Department of Stomatology, Shenzhen University General Hospital（深圳大学总医院口腔科）
NVIDIA（英伟达）；Georgia Institute of Technology（佐治亚理工学院）；NVIDIA Research（英伟达研究院）
Acquisition and creation of digital human avatars is an important problem with applications to virtual telepresence, gaming, and human modeling. Most contemporary approaches for avatar generation can be viewed either as 3D-based methods, which use multi-view data to learn a 3D representation with appearance (such as a mesh, implicit surface, or volume), or 2D-based methods which learn photo-realistic renderings of avatars but lack accurate 3D representations. In this work, we present, DRaCoN, a framework for learning full-body volumetric avatars which exploits the advantages of both the 2D and…
