Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “3D generation”
GCDM generates valid large 3D molecules and optimizes existing molecules.
problem Lack of geometric properties in 3D molecule generation models.
method Introduces Geometry-Complete Diffusion Model (GCDM) using equivariant GNNs.
result Significantly outperforms existing models in 3D molecule generation and optimization.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
A framework for generating 3D shapes by sequentially assembling primitives.
problem Combinatorial complexity in generating 3D shapes.
method Bayesian optimization for efficient exploration and exploitation of feasible combinations.
result Successfully generates realistic combinatorial 3D shapes.
Equivariant diffusion model generates 3D molecules efficiently.
problem Generating high-quality 3D molecules efficiently.
method Equivariant Diffusion Model (EDM) that operates on atom coordinates and types.
result Significantly outperforms previous methods in molecule quality and training efficiency.
VecMol generates 3D molecules as continuous vector fields, overcoming modality and geometry constraints.
problem Challenges in generating 3D molecules, especially in drug discovery and materials science.
method VecMol reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, parameterized by a neural field and generated using a latent diffusion model.
result Vector-field-based representations show promise for 3D molecular generation, validated on benchmarks.
for 3d theorieshep-th
Proposes a new effective central charge for 3d N=2 theories.
problem Understanding the effective central charge in 3d N=2 theories.
method Analyzes the superconformal index to propose a new quantity and discusses its properties and computation.
result Proposes a new effective central charge for 3d N=2 theories.
Smooth 3D flows from non-smooth starting points.
problem Creating smooth Ricci flows from non-smooth initial conditions.
method Generalized singular Ricci flow applied to 3D complete manifolds.
result Existence of smooth Ricci flows starting from non-smooth initial conditions.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
problem Impersonation attacks using master faces for face-based identity authentication.
method Evolutionary algorithm in latent space of StyleGAN, neural network to direct search, 2D and 3D face reconstruction.
result Obtains high impersonation rates with fewer master faces for 2D and 3D face verification.
Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations. Reducing both task complexity and the amount of task switching done by annotators is key to reducing the effort and time required to generate 3D bounding box annotations. This paper…
Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational AutoEncoders which have shown great promise for learning rich representations of deformab…
ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.
3D dual field theories for Virasoro minimal models constructed using Seifert fiber spaces.
problem Constructing 3D dual field theories for Virasoro minimal models.
method 3D-3D correspondence and Seifert fiber spaces.
result 3D dual field theories constructed for Virasoro minimal models.
StyleNeRF generates high-resolution images with 3D consistency and style control.
problem Generating high-resolution images with fine details and 3D consistency.
method Integrates NeRF into a style-based generator for efficient high-resolution image synthesis.
result Synthesizes high-resolution images at interactive rates with high 3D consistency and style control.
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representationcs.CV
Pix2Shape learns 3D scene representations from single images without supervision.
problem Learning 3D scene information from a single image without supervision.
method Pix2Shape uses an encoder, decoder, and critic network to generate 2.5D surfel-based reconstructions.
result Pix2Shape can generate complex 3D scenes from a single image, scaling with on-screen resolution.
LION generates high-quality 3D shapes using hierarchical latent diffusion models.
problem Creating high-quality 3D shapes for digital artists.
method Hierarchical Latent Point Diffusion Model (LION) with a global shape latent and point-structured latent space.
result LION achieves state-of-the-art generation performance on ShapeNet benchmarks.
DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.
problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.
Proposes a model to generate 3D-aware images from 2D images.
problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.
We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining par…
Recent years have witnessed the emergence of 3D medical imaging techniques with the development of 3D sensors and technology. Due to the presence of noise in image acquisition, registration researchers focused on an alternative way to represent medical images. An alternative way to analyze medical imaging is by underst…
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer\{'}s disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocamp…
New RL method designs 3D molecules with improved symmetry.
problem Lack of 3D information in molecular design.
method Symmetry-aware actor-critic architecture using spherical harmonics.
result Improves generalization and molecule quality.
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer's disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocampus …
The study connects knot complements to 3d theories via half-index calculations.
problem Understanding the relationship between knot complements and 3d theories.
method Using half-index calculations and inverted Habiro series, the study realizes knot complements as homological blocks.
result The colored Jones polynomial is derived from choosing specific poles in the half-index integral expression.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
The paper tackles mapping tori by proposing a new approach to 3d-3d correspondence.
problem No existing approach fully describes 3d SCFTs for all types of 3-manifolds.
method Systematic study of 3d gauge theories with non-linear matter fields.
result Recovery of 3-manifold invariants from indices and proposal of new -series invariants.
The paper studies decay near singularities of 3d Yang-Mills-Higgs fields.
problem Understanding isolated singularities of 3d Yang-Mills-Higgs fields.
method Derives decay estimates and applies removable singularity theorems.
result Generalizes removable singularity theorems for 3d Yang-Mills-Higgs fields.
NeRF-VAE generates 3D scenes with geometric structure from few images.
problem Generating 3D scenes from few images with geometric consistency.
method Combines NeRF and VAE, incorporating shared geometric structure.
result NeRF-VAE can infer and render geometrically-consistent scenes from unseen environments.
Dimofte, Gaiotto and Gukov introduced a powerful invariant, the 3D-index, associated to a suitable ideal triangulation of a 3-manifold with torus boundary components. The 3D-index is a collection of formal power series in with integer coefficients. Our goal is to explain how the 3D-index is a generating serie…
3D models vulnerable to adversarial attacks, new method improves success rate and naturalness.
problem Vulnerability of 3D deep learning models to adversarial examples in the physical world.
method ε-isometric (-ISO) attack considering geometric properties and invariance to physical transformations.
result Significantly improved attack success rate and naturalness of 3D adversarial examples.
We present a method of generating high resolution 3D shapes from natural language descriptions. To achieve this goal, we propose two steps that generating low resolution shapes which roughly reflect texts and generating high resolution shapes which reflect the detail of texts. In a previous paper, the authors have show…
Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of o…
New framework predicts diverse, contextually plausible 3D human motions.
problem Predicting multiple plausible future 3D poses given observed poses.
method Developed a new variational framework that conditions latent variable on past observation to encourage relevant information.
result Our approach generates motions of higher quality and preserves contextual information.
New framework for 3D spatial topology enumeration and identification.
problem Efficient navigation through complex engineering system topologies.
method Mathematical spatial graph theory to represent, enumerate, and identify unique topological classes.
result Identification of distinctive 3D topological classes for engineering systems.
This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.
problem Creating large datasets for deep learning in computer vision.
method 3D facial modelling techniques and deep learning methodologies.
result Synthetic 3D thermal facial data created for deep learning applications.
Using generative models for Inverse Graphics is an active area of research. However, most works focus on developing models for supervised and semi-supervised methods. In this paper, we study the problem of unsupervised learning of 3D geometry from single images. Our approach is to use a generative model that produces 2…
3D object detection improved using energy-based models.
problem Accurate 3D object detection in cluttered environments from sparse LiDAR data.
method Designing a differentiable pooling operator for 3D bounding boxes integrated into a state-of-the-art 3D object detector.
result Our approach consistently outperforms the SA-SSD baseline across all 3DOD metrics on the KITTI dataset.
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…
We study knots in 3d Chern-Simons theory with complex gauge group , in the context of its relation with 3d theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d theory, which is compactified on a 3-manifold . …
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
problem Challenges in data efficiency, obstacle avoidance, and generalization in 3D visual navigation.
method Incorporates attention on 3D spatial relationships and a target skill extension module into DRL framework.
result Significantly improves navigation performance and generalization across targets and scenes.
Study periodic geodesics on contact 3D manifolds, proving existence and precise properties.
problem Existence and properties of periodic geodesics in contact sub-Riemannian metrics.
method Develops two independent subjects: existence of spiraling geodesics and precise study of geodesics on quotient of SL2(R).
result Proves existence and precise properties of periodic geodesics.
In this paper, we extend and complete the classification of the generic singularities of the 3D-contact sub-Riemmanian conjugate locus in a neighbourhood of the origin.
We show that 3D gravity, in its pure connection formulation, admits a natural 6D interpretation. The 3D field equations for the connection are equivalent to 6D Hitchin equations for the Chern-Simons 3-form in the total space of the principal bundle over the 3-dimensional base. Turning this construction around one gets …
A new method for generating realistic and creative 3D shapes from point clouds.
problem Generating realistic and creative 3D shapes from point clouds.
method Learning to interpolate point clouds by encoding prior knowledge about real-world objects.
result Generated 3D shapes are both realistic and creative, unlike any existing forms.
Study of IR phases in 3D class R theories linked to non-hyperbolic 3-manifolds.
problem Understanding IR phases of 3D class R theories associated with non-hyperbolic 3-manifolds.
method Analysis of IR phenomena through `exceptional' Dehn fillings and gauging of flavor symmetries.
result 3D class R theories associated with certain atoroidal non-hyperbolic 3-manifolds exhibit supersymmetry enhancement at low energy.
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to t…
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
problem Lack of explicit geometric information in 3D semantic segmentation models.
method Introduces GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into existing 3D segmentation pipelines.
result Consistent performance gains across multiple benchmarks, including up to +11.5% mIoU on TS40K with PTV3.