ReConText3D is the first replay-memory framework for continual text-to-3D generation that prevents catastrophic forgetting on new textual categories while preserving quality on previously seen classes.
hub Mixed citations
Shap-E: Generating Conditional 3D Implicit Functions
Mixed citation behavior. Most common role is background (62%).
54
Pith papers citing it
114
external citations · Pith
Background
62% of classified citations
abstract
We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields. We train Shap-E in two stages: first, we train an encoder that deterministically maps 3D assets into the parameters of an implicit function; second, we train a conditional diffusion model on outputs of the encoder. When trained on a large dataset of paired 3D and text data, our resulting models are capable of generating complex and diverse 3D assets in a matter of seconds. When compared to Point-E, an explicit generative model over point clouds, Shap-E converges faster and reaches comparable or better sample quality despite modeling a higher-dimensional, multi-representation output space. We release model weights, inference code, and samples at https://github.com/openai/shap-e.
hub tools
citation-role summary
background 6
baseline 1
other 1
citation-polarity summary
representative citing papers
3D-CoS represents 3D objects as Blender code generated by VLMs, with workflows for planning, RAG, and agents, showing better edit fidelity than point-cloud baselines.
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
OmniFaceRig automates creation of FACS blendshapes and inner-mouth geometry for diverse 3D character topologies from surface-only meshes using hybrid VLM+CV parsing, template registration, and procedural fitting.
PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.
Text2CAD-Bench supplies 600 dual-prompt examples across four geometric and domain levels to test LLMs on text-to-parametric CAD, finding solid basic performance but sharp drops on complex topology and advanced features.
Introduces the first passive source attribution benchmark for 22 generative 3D models and a Transformer achieving 97.22% accuracy under full supervision and 77.17% with 1% training data.
3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
Affostruction reconstructs full 3D object geometry from partial RGBD views and grounds text-based affordances on both visible and unobserved surfaces, reporting large gains over prior methods.
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.
FLUX3D introduces Diffusion-Aligned Structured Latents (DA-SLAT) and Sparse-structure Multimodal Diffusion Transformer (SMDiT) with MARoPE to address representation and alignment bottlenecks in sparse-voxel 3DGS generation.
A training-free two-stage pipeline uses cross-space dual-branch denoising with CLIP-guided voxel alignment and SDF blending for geometry, followed by view-conditioned 2D diffusion texture projection, to produce dual-semantic 3D illusions in 3-5 minutes.
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.
DB-3DME supplies a human-rated 3D mesh dataset and shows that fine-tuning the visual encoder of Qwen-2.5-VL-7B produces automatic evaluations that align better with humans than prior VLMs.
EditSSC converts 3D semantic occupancy to multi-channel BEV images and runs latent diffusion on Stable Diffusion's quantized autoencoder and UNet to achieve unconditional generation plus training-free sketch-guided editing, inpainting and outpainting, outperforming 3D baselines on SemanticKITTI.
Fishbone introduces a unified rib-spine representation computed via adaptive heat method, iso-contour ribs, and geometry-aware spine that enables real-time parametric deformation, reduced-space simulation, and animation on general meshes.
citing papers explorer
-
ReConText3D: Replay-based Continual Text-to-3D Generation
ReConText3D is the first replay-memory framework for continual text-to-3D generation that prevents catastrophic forgetting on new textual categories while preserving quality on previously seen classes.
-
3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
3D-CoS represents 3D objects as Blender code generated by VLMs, with workflows for planning, RAG, and agents, showing better edit fidelity than point-cloud baselines.
-
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
-
OmniFaceRig: Fully Automatic Inner-Mouth-Aware Face Rigging Across Diverse 3D Character Topologies
OmniFaceRig automates creation of FACS blendshapes and inner-mouth geometry for diverse 3D character topologies from surface-only meshes using hybrid VLM+CV parsing, template registration, and procedural fitting.
-
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.
-
Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation
Text2CAD-Bench supplies 600 dual-prompt examples across four geometric and domain levels to test LLMs on text-to-parametric CAD, finding solid basic performance but sharp drops on complex topology and advanced features.
-
Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models
Introduces the first passive source attribution benchmark for 22 generative 3D models and a Transformer achieving 97.22% accuracy under full supervision and 77.17% with 1% training data.
-
Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion
3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
-
Affostruction: 3D Affordance Grounding with Generative Reconstruction
Affostruction reconstructs full 3D object geometry from partial RGBD views and grounds text-based affordances on both visible and unobserved surfaces, reporting large gains over prior methods.
-
SVG360: Editable Multiview Vector Graphics from a Single SVG
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
-
Structured 3D Latents for Scalable and Versatile 3D Generation
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
-
LRM: Large Reconstruction Model for Single Image to 3D
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
-
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
-
Objaverse-XL: A Universe of 10M+ 3D Objects
Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.
-
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.
-
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
FLUX3D introduces Diffusion-Aligned Structured Latents (DA-SLAT) and Sparse-structure Multimodal Diffusion Transformer (SMDiT) with MARoPE to address representation and alignment bottlenecks in sparse-voxel 3DGS generation.
-
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
A training-free two-stage pipeline uses cross-space dual-branch denoising with CLIP-guided voxel alignment and SDF blending for geometry, followed by view-conditioned 2D diffusion texture projection, to produce dual-semantic 3D illusions in 3-5 minutes.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.
-
DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation
DB-3DME supplies a human-rated 3D mesh dataset and shows that fine-tuning the visual encoder of Qwen-2.5-VL-7B produces automatic evaluations that align better with humans than prior VLMs.
-
EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models
EditSSC converts 3D semantic occupancy to multi-channel BEV images and runs latent diffusion on Stable Diffusion's quantized autoencoder and UNet to achieve unconditional generation plus training-free sketch-guided editing, inpainting and outpainting, outperforming 3D baselines on SemanticKITTI.
-
Fishbone: From One 3D Asset to a Million Controllable Edits
Fishbone introduces a unified rib-spine representation computed via adaptive heat method, iso-contour ribs, and geometry-aware spine that enables real-time parametric deformation, reduced-space simulation, and animation on general meshes.
-
REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
REVIVE 3D generates voluminous 3D assets from flat 2D images via an inflated prior construction followed by latent-space refinement, plus new metrics for volume and flatness validated by user study.
-
Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows
Point-MF performs one-step point cloud reconstruction from single images by learning a mean velocity field in point space with a tailored Diffusion Transformer and a new auxiliary loss.
-
Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.
-
SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation
SIC3D generates text-to-3D objects with Gaussian splatting then stylizes them using Variational Stylized Score Distillation loss plus scaling regularization to improve style match and geometry fidelity.
-
Native and Compact Structured Latents for 3D Generation
Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials than prior methods.
-
Scaling Sequence-to-Sequence Generative Neural Rendering
Kaleido is a masked autoregressive generative model that unifies 3D view synthesis and video modeling by pre-training a single transformer on video data, achieving SOTA zero-shot and many-view performance on view synthesis benchmarks.
-
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
-
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
InstantMesh produces diverse, high-quality 3D meshes from single images in seconds by combining a multi-view diffusion model with a sparse-view large reconstruction model and optimizing directly on meshes.
-
BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
BoostDream refines coarse feed-forward text-to-3D assets via 3D distillation, multi-view SDS loss from a 2D diffusion model, and prompt-consistent normal maps to produce higher-quality results more efficiently than standard SDS.
-
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
-
MVDream: Multi-view Diffusion for 3D Generation
MVDream is a multi-view diffusion model that functions as a generalizable 3D prior, enabling more consistent text-to-3D generation and few-shot 3D concept learning from 2D examples.
-
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
Introduces vitality-aware compression for image-to-3D DiT models via structured pruning, adaptive quantization, and fine-tuning, claiming 66% size reduction with comparable fidelity.
-
T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
A text-to-LiDAR diffusion model with self-conditioned reconstruction guidance, directional position encoding, and two >100K-pair benchmarks, supporting multiple conditioning modalities.
-
SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration
SceneConductor decomposes single-image 3D scene generation into initialization, environment construction, and multi-agent refinement stages with a geometry-aware layout predictor trained on sparse geometric priors from point maps.
-
Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment
Native3D introduces a direct 3D scene generation method using unified mesh-texture representation and 3D REPA Loss for semantic alignment, claimed to outperform prior 2D-dependent approaches.
-
Structural Energy Guidance for View-Consistent Text-to-3D Generation
SEGS constructs structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process to improve multi-view consistency in text-to-3D generation.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion
DecoRec decomposes single-view 3D scene reconstruction into per-object diffusion reconstructions followed by a differentiable rendering and diffusion-guided merging pipeline.
-
EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers
EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.
-
SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design
SpatialPrompt turns spatial sketches and voice prompts into executable constraints for controllable AI 3D generation in XR, enabling iterative collaborative creation with color-coded contributions.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
Unposed-to-3D learns simulation-ready 3D vehicle models from unposed real images by predicting camera parameters for photometric self-supervision, then adding scale prediction and harmonization.
-
VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
VecSet-Edit edits a mesh by masking and re-denoising a subset of its VecSet latent tokens, preserving untouched regions better than prior voxel-based editors.
-
XARP Tools: An Extended Reality Platform for Humans and AI Agents
XARP provides a WebSocket-based remote-procedure system that lets Python code and AI agents control Unity XR clients, with benchmarks and user studies showing faster iteration than conventional XR workflows.
-
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
ConsDreamer refines conditional and unconditional terms in score distillation via view disentanglement and geometric consistency loss to reduce the Janus problem in zero-shot text-to-3D.
-
ABot-Earth 0.5: Generative 3D Earth Model
ABot-Earth 0.5 is a 3DGS-based generative model trained on real-world urban reconstructions that synthesizes novel 3D scenes from satellite imagery in under 10 minutes per square kilometer.