X-Splat is the first Gaussian Splatting method that reconstructs CBCT-like 3D dental volumes from a single panoramic radiograph by constraining learnable Gaussians to panoramic geometry and adding a residual anatomical refiner.
hub Mixed citations
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Mixed citation behavior. Most common role is background (64%).
79
Pith papers citing it
Background
64% of classified citations
abstract
We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g, depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.
hub tools
citation-role summary
background 8
baseline 3
citation-polarity summary
representative citing papers
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toys4K in Chamfer and Hausdorff distances.
Arbor attaches constraint mesh tokens to a frozen text-to-3D denoiser to enable controllable generation obeying hull, avoidance, and touch constraints.
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
A method that treats 3D box pairs as exact transformation specs, adds a depth-aware floor reference, and trains an image generator on synthetic scenes plus Objectron videos to perform large 3D edits on real photographs.
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.
GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
MeshFIM enables local low-poly mesh editing by autoregressively filling target regions conditioned on context, using boundary markers, positional embeddings, and a gated geometry encoder to enforce attachment, topology, and region limits.
Mix3R mixes feed-forward reconstruction and generative 3D priors via Mixture-of-Transformers and overlap-based attention bias to achieve better-aligned 3D shapes and more accurate poses than either approach alone.
DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.
AGILE generates complete object meshes via VLM-guided synthesis and tracks poses with anchor-and-track plus contact-aware optimization to achieve robust hand-object reconstruction from video.
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.
A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.
Voxify3D generates voxel art from 3D meshes via orthographic pixel supervision, patch-based CLIP alignment, and palette-constrained Gumbel-Softmax quantization, achieving 37.12 CLIP-IQA and 77.90% user preference.
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
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.
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
Introduces SPECSIA-15K dataset and DraViE module to improve novel-view fidelity and temporal coherence in drawing-based 3D animation.
CORGI reconstructs high-fidelity, animatable 3D dogs from a single in-the-wild image via canonical orbital generation, deformable 3DGS anchored to D-SMAL, and self-supervised generative repair, without 3D supervision.
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
citing papers explorer
-
X-Splat: Gaussian Splatting for 3D CBCT Generation from Single Panoramic Radiograph
X-Splat is the first Gaussian Splatting method that reconstructs CBCT-like 3D dental volumes from a single panoramic radiograph by constraining learnable Gaussians to panoramic geometry and adding a residual anatomical refiner.
-
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toys4K in Chamfer and Hausdorff distances.
-
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Arbor attaches constraint mesh tokens to a frozen text-to-3D denoiser to enable controllable generation obeying hull, avoidance, and touch constraints.
-
MeshFlow: Mesh Generation with Equivariant Flow Matching
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
-
Thinking in Boxes: 3D Editing in Real Images Made Easy
A method that treats 3D box pairs as exact transformation specs, adds a depth-aware floor reference, and trains an image generator on synthetic scenes plus Objectron videos to perform large 3D edits on real photographs.
-
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.
-
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
MeshFIM enables local low-poly mesh editing by autoregressively filling target regions conditioned on context, using boundary markers, positional embeddings, and a gated geometry encoder to enforce attachment, topology, and region limits.
-
Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
Mix3R mixes feed-forward reconstruction and generative 3D priors via Mixture-of-Transformers and overlap-based attention bias to achieve better-aligned 3D shapes and more accurate poses than either approach alone.
-
DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.
-
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
-
THOM: Generating Physically Plausible Hand-Object Meshes From Text
THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.
-
AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
AGILE generates complete object meshes via VLM-guided synthesis and tracks poses with anchor-and-track plus contact-aware optimization to achieve robust hand-object reconstruction from video.
-
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.
-
Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters
A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.
-
Voxify3D: Pixel Art Meets Volumetric Rendering
Voxify3D generates voxel art from 3D meshes via orthographic pixel supervision, patch-based CLIP alignment, and palette-constrained Gumbel-Softmax quantization, achieving 37.12 CLIP-IQA and 77.90% user preference.
-
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.
-
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.
-
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
-
SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation
Introduces SPECSIA-15K dataset and DraViE module to improve novel-view fidelity and temporal coherence in drawing-based 3D animation.
-
CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild
CORGI reconstructs high-fidelity, animatable 3D dogs from a single in-the-wild image via canonical orbital generation, deformable 3DGS anchored to D-SMAL, and self-supervised generative repair, without 3D supervision.
-
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
-
HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches
HandMade converts segmented VR strokes into multi-view part guidance and structured prompts so generative 3D models better preserve user-specified spatial scaffolds than text-only or sketch baselines.
-
SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
SubdivAR reformulates neural mesh subdivision as autoregressive next-scale vertex-offset prediction, reporting 18.8% lower Hausdorff and 14.2% lower Chamfer distance than NMR on closed meshes.
-
Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication
GenMF refines generated 3D meshes to encode appearance cues as geometry for monochromatic fabrication while minimizing fabrication stress.
-
HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors
HiFiVe is a training-free framework using an auto-regressive texture refinement pipeline with depth-based warping, multi-view fusion, and symmetry to enhance both texture and geometry fidelity in vehicle generation from 2D priors.
-
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.
-
$\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction
φ-Scene performs image-to-3D scene reconstruction via topology-driven physical assembly that resolves penetrations with SDF optimization and settles objects with rigid-body simulation.
-
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.
-
ReAge3D: Re-Aging 3D Faces with View Consistency
ReAge3D trains a diffusion re-aging model on synthetic pairs then uses masked propagation from a frontal pivot view to produce consistent multi-view images that supervise 3D face optimization.
-
Surflo: Consistent 3D Surface Flow Model with Global State
Surflo compresses unposed RGB views into K global latent tokens and uses flow matching with photometric guidance to decode consistent arbitrary-resolution 3D surface points in one forward pass.
-
DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation
DeepJEB++ expands a small seed set of jet engine brackets into 15,360 labeled 3D designs via 2D latent diffusion augmentation, VLM filtering, generative 3D lifting, and automated finite-element labeling.
-
TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization
TextHOI-3D generates text-conditioned 3D hand-object meshes using a VQ token space and CLIP-conditioned autoregressive multi-view prediction followed by joint mesh optimization, reporting large reductions in object CD and penetration volume versus single-view baselines on HO3D-derived data.
-
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.
-
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects
PhysX-Omni unifies simulation-ready 3D asset generation across rigid, deformable, and articulated objects via a new geometry representation, the PhysXVerse dataset, and the PhysX-Bench evaluation suite.
-
ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation
ROAR-3D adds a token-wise view router and dual-stream attention to pretrained single-view 3D generators so they can use arbitrary unposed images for higher-fidelity output.
-
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.
-
Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
HA-HOI produces physically plausible 4D HOI animations from monocular videos by anchoring object reconstruction to human motion and refining the result in a physics-based humanoid-object simulator.
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
-
MiXR: Harvesting and Recomposing Geometry from Real-World Objects for In-Situ 3D Design
MiXR enables in-situ 3D compositional modeling by harvesting real-world geometry in XR and using generative AI to synthesize coherent models from user-defined assemblies.
-
Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
OneViewAll reports 92.5% ADD-0.1 pose accuracy on LINEMOD from a single real reference RGB-D view, using projection-based refinement with mirror-fusion symmetry priors rather than CAD rendering.
-
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
PhysForge generates physics-grounded 3D assets via a VLM-planned Hierarchical Physical Blueprint and a KineVoxel Injection diffusion model, backed by the new PhysDB dataset of 150,000 annotated assets.
-
MeshReGen: A Unified 3D Geometry Regeneration Framework
MeshReGen introduces a conditioned 3D geometry regenerator with VecSet that learns a regeneration prior via self-supervision and reports state-of-the-art results on controllable generation tasks.
-
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.
-
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
RecGen achieves state-of-the-art 3D multi-object scene reconstruction from sparse RGB-D views by combining compositional synthetic scene generation with strong 3D shape priors, outperforming SAM3D by 30%+ in shape quality and pose accuracy while using 80% fewer meshes.
-
Repurposing 3D Generative Model for Autoregressive Layout Generation
LaviGen turns 3D generative models into an autoregressive layout generator that models geometric and physical constraints, delivering 19% higher physical plausibility and 65% faster inference on the LayoutVLM benchmark.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
Grasp as You Dream: Imitating Functional Grasping from Generated Human Demonstrations
GraspDreamer synthesizes human functional grasping demonstrations with visual generative models to enable zero-shot robot grasping with improved data efficiency and generalization.