Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.
hub Canonical reference
Native and Compact Structured Latents for 3D Generation
Canonical reference. 80% of citing Pith papers cite this work as background.
35
Pith papers citing it
Background
80% of classified citations
abstract
Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.
hub tools
citation-role summary
background 8
method 2
citation-polarity summary
years
2026 35representative citing papers
Image-to-3D models successfully generate harmful geometries in most cases with under 0.3% caught by commercial filters; existing safeguards are weak but a stacked defense cuts harmful outputs to under 1% at 11% false-positive cost.
A new pipeline using canonical LoRAs for view synthesis, deformable 3D Gaussian splatting anchored on D-SMAL, and generative repair to produce animatable 3D dogs from single wild images without 3D supervision.
WiSER introduces a transmitter-conditioned sparse 3D scene encoder queried by a ray-corridor decoder for radiomaps and a DETR-style set decoder for variable-cardinality CIR taps, trained on co-registered ScanNet++ and Sionna data.
Pxform provides 100K semantic-part 3D edit pairs; PartFlow uses them to deliver feedforward 3D editing with improved fidelity and preservation over prior methods.
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.
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
Multi-grained counting is introduced with five granularity levels, supported by the new KubriCount dataset generated via 3D synthesis and editing, and HieraCount model that combines text and visual exemplars for improved accuracy.
VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in realism and consistency.
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
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.
ShellMaker generates complete building exteriors from scaffolds and style prompts via parametric roofs, LLM prompt refinement, material retrieval, and geometry-aware assembly while preserving structural constraints.
3DMorph transfers local modifications from a single edited 2D image to the corresponding regions of a 3D mesh without training and supports shape morphing between original and edited versions.
MORPHOS introduces an autoregressive 4D generation method with Temporal Structured Latents (T-SLAT) that produces dynamic 3D assets from videos while handling topological changes and long sequences.
Helix4D generates high-quality dynamic 4D meshes from videos by extending Trellis2 with sliding-window cross-frame attention anchored on the first frame and a repurposed 4D temporal encoding.
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.
Stream3D is a training-free method that maintains a fixed-size evidential memory of past frames to convert frozen view-conditioned 3D generators into consistent streaming generators.
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.
Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
DVD applies discrete diffusion directly to voxel occupancy for 3D generation, uncertainty estimation via entropy, and single-round editing via block perturbation fine-tuning.
LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.
citing papers explorer
-
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.
-
On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models
Image-to-3D models successfully generate harmful geometries in most cases with under 0.3% caught by commercial filters; existing safeguards are weak but a stacked defense cuts harmful outputs to under 1% at 11% false-positive cost.
-
CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild
A new pipeline using canonical LoRAs for view synthesis, deformable 3D Gaussian splatting anchored on D-SMAL, and generative repair to produce animatable 3D dogs from single wild images without 3D supervision.
-
WiSER: A Wireless Scene Encoder for Geometry-Grounded Multi-View Wireless Prediction
WiSER introduces a transmitter-conditioned sparse 3D scene encoder queried by a ray-corridor decoder for radiomaps and a DETR-style set decoder for variable-cardinality CIR taps, trained on co-registered ScanNet++ and Sionna data.
-
Feedforward 3D Editing Learns from Semantic-Part Transformation
Pxform provides 100K semantic-part 3D edit pairs; PartFlow uses them to deliver feedforward 3D editing with improved fidelity and preservation over prior methods.
-
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.
-
The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
-
Count Anything at Any Granularity
Multi-grained counting is introduced with five granularity levels, supported by the new KubriCount dataset generated via 3D synthesis and editing, and HieraCount model that combines text and visual exemplars for improved accuracy.
-
Velocity-Space 3D Asset Editing
VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.
-
Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in realism and consistency.
-
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
-
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
-
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.
-
ShellMaker: Language-Guided Exterior Completion under Structural Constraints
ShellMaker generates complete building exteriors from scaffolds and style prompts via parametric roofs, LLM prompt refinement, material retrieval, and geometry-aware assembly while preserving structural constraints.
-
3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing
3DMorph transfers local modifications from a single edited 2D image to the corresponding regions of a 3D mesh without training and supports shape morphing between original and edited versions.
-
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
MORPHOS introduces an autoregressive 4D generation method with Temporal Structured Latents (T-SLAT) that produces dynamic 3D assets from videos while handling topological changes and long sequences.
-
Helix4D: Complex 4D Mesh Generation
Helix4D generates high-quality dynamic 4D meshes from videos by extending Trellis2 with sliding-window cross-frame attention anchored on the first frame and a repurposed 4D temporal encoding.
-
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.
-
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
Stream3D is a training-free method that maintains a fixed-size evidential memory of past frames to convert frozen view-conditioned 3D generators into consistent streaming generators.
-
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.
-
Pixal3D: Pixel-Aligned 3D Generation from Images
Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.
-
Generative 3D Gaussians with Learned Density Control
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
-
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
DVD applies discrete diffusion directly to voxel occupancy for 3D generation, uncertainty estimation via entropy, and single-round editing via block perturbation fine-tuning.
-
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.
-
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
VolFill uses a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into latent space and a latent Diffusion Transformer to denoise complete scenes, conditioned on geometry foundation models, outperforming baselines on SCRREAM and NRGB-D datasets.
-
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
SuperVoxelGPT creates shape-adaptive, deterministically ordered supervoxel tokens via saliency-guided CVT, cutting sequence length to 12.8% of uniform voxels while claiming SOTA quality and 10x speedup on Trellis-500K.
-
AssetGen: Deployable 3D Asset Generation at Interactive Speed
AssetGen is a system that produces deployable 3D assets including meshes, baked normals, and textures from a single reference image in under 30 seconds via a coarse-to-refine VecSet pipeline and co-designed optimizations.
-
CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation
CMAG combines 3D concept scaffolding, prompt decomposition, taxonomy routing, hybrid retrieval, and agentic VLM verification to assemble topologically consistent avatars from catalog assets given free-form text prompts.
-
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.
-
Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter
EnDKF combines ensemble Kalman filtering with directional statistics and unit quaternions to achieve lower pose tracking error than raw measurements in synthetic constant-velocity tests and FoundationPose-based head tracking.
-
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.
-
Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
Asset Harvester converts sparse in-the-wild object observations from AV driving logs into complete simulation-ready 3D assets via data curation, geometry-aware preprocessing, and a SparseViewDiT model that couples sparse-view multiview generation with 3D Gaussian lifting.
-
Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation
Hitem3D 2.0 combines multi-view image synthesis with native 3D texture projection to improve completeness, cross-view consistency, and geometry alignment over prior methods.
-
Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
Seed3D 2.0 advances 3D content generation via a coarse-to-fine geometry pipeline, unified PBR material model, and simulation-ready scene tools, reporting 69-89.9% win rates over commercial systems in human studies.
-
3D Generation for Embodied AI and Robotic Simulation: A Survey
The paper surveys 3D generation techniques for embodied AI and robotics, categorizing them into data generation, simulation environments, and sim-to-real bridging while identifying bottlenecks in physical validity and transfer.