Skip to content

About

A curated list of awesome AIGC 3D papers

Resources

Contributing

Stars

788 stars

Watchers

27 watching

Forks

Latest commit

Β 

History

270 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

From Visual Synthesis to Interactive Worlds:
Toward Production-Ready 3D Asset Generation

arXiv Project Page GitHub stars License

Jiafeng Wu1,2*† Β Β·Β  Zhuofan Lou1,3*† Β Β·Β  Jian Liu1‑
Chunchao Guo4 Β Β·Β  Dazhao Du1 Β Β·Β  Song Guo1Β§

1 The Hong Kong University of Science and Technology
2 Huazhong University of Science and Technology Β Β·Β  3 Sichuan University Β Β·Β  4 Tencent

* Equal contribution Β Β·Β  † Work done during internship at HKUST Β Β·Β  ‑ Project lead Β Β·Β  Β§ Corresponding author

✦ Production-Oriented 3D Generation Survey ✦

🧭 Taxonomy Β· πŸ—‚ Data Β· πŸ“¦ Objects Β· 🧍 Characters Β· 🌍 Scenes Β· πŸ“ Evaluation Β· 🏭 Industry

News

  • πŸ”₯ [2026-04] v2.0: Introduces a production-ready two-dimensional taxonomy spanning asset tiers and pipeline stages, and expands the collection to data foundations, geometry, topology, appearance, rigging, scene assembly, evaluation, and industry systems.
  • πŸ“š [2025-08] v1.0: Established the initial curated 3D AIGC paper collection, organized object, scene, and avatar methods under 3D-native, 2D-prior, and hybrid paradigms, and tracked surveys, datasets, talks, companies, and implementations.

Abstract

Three-dimensional content generation has progressed from producing isolated, visually plausible shapes to constructing structured assets that can be deployed in real-time interactive environments. This trajectory is driven by converging demands from game development, embodied AI, world simulation, digital twins, and spatial computing, all of which require 3D content that goes beyond surface appearance to satisfy engine-level constraints on topology, UV parameterization, physically based materials, skeletal rigging, and physics-aware scene layout. Despite rapid advances in generative modeling, a persistent gap separates the outputs of current methods from the production-ready standard expected by interactive applications. This survey addresses that gap by organizing the literature around the asset production pipeline rather than algorithmic families.

At a Glance

  • 🧭 Organized by a production-ready, pipeline-first taxonomy rather than isolated algorithm families.
  • πŸ“¦ Covers three asset tiers: general objects, characters and avatars, and scenes and environments.
  • πŸ›  Tracks the full asset workflow from data foundations through geometry, topology, appearance, rigging, and scene assembly.
  • πŸ“š Consolidates methods, datasets, evaluation criteria, and industry references in one companion list.

Table of Contents


Survey Taxonomy

The survey is organized around a two-dimensional taxonomy:

  • Horizontal axis (asset types): General Objects, Characters & Avatars, Scenes & Environments
  • Vertical axis (pipeline stages): Data Foundations β†’ Geometry β†’ Topology β†’ Appearance β†’ Rigging β†’ Scene Assembly

This structure mirrors the production pipeline used in game engines and interactive applications, enabling direct assessment of where each method fits within a deployment workflow.


Data Foundations & Benchmarks

Object Datasets

Dataset Year Scale Description
ShapeNet 2015 51K models, 55 categories Large-scale 3D shape repository (Chang et al.)
ModelNet 2015 12K CAD models, 40 categories Princeton 3D object benchmark (Wu et al.)
ABC 2019 1M+ CAD models Mechanical parts with parametric annotations (Koch et al.)
Thingi10K 2016 10K printable models Web-derived 3D printing models with diverse topology (Zhou and Jacobson)
PartNet 2019 27K objects, 573K parts Part-level object annotations for structural decomposition (Mo et al.)
Text2Shape 2018 75K text-shape pairs Paired text and shape corpus for language-conditioned 3D generation (Chen et al.)
GSO (Google Scanned Objects) 2022 1K+ scans Household objects with PBR materials (Downs et al.)
ABO (Amazon Berkeley Objects) 2022 8K+ models Product catalog with multi-view images (Collins et al.)
CO3D 2021 1.5M frames, 19K objects Multi-view real-capture object dataset for category-level reconstruction (Reizenstein et al.)
Objaverse 2023 800K+ objects Internet-scale 3D asset collection (Deitke et al.)
Objaverse-XL 2024 10.2M objects Extended internet-scale collection (Deitke et al.)

Character Datasets

Dataset Year Scale Description
FAUST 2014 300 scans, 10 subjects Real body scans with ground-truth correspondence (Bogo et al.)
RenderPeople 2018 4.5K+ subjects Commercially scanned textured human meshes for character production (RenderPeople)
AMASS 2019 Large-scale motion capture Unified motion capture archive (Mahmood et al.)
CAPE 2020 4D clothing Clothed body scans with pose variation (Ma et al.)
THuman2.0 2021 526 high-res scans Detailed textured human models (Yu et al.)
HuMMan 2022 1K subjects Multi-modal human dataset (Cai et al.)
HumanML3D 2022 14.6K text-motion sequences Text-aligned motion corpus for controllable human generation and evaluation (Guo et al.)
Motion-X 2024 Large-scale motion Expressive whole-body motion dataset (Lin et al.)

Scene Datasets

Dataset Year Scale Description
ScanNet 2017 1,513 indoor scans RGB-D reconstructions with annotations (Dai et al.)
ScanNet++ 2023 460 scenes Laser+DSLR indoor scans with material annotations (Yeshwanth et al.)
Matterport3D 2017 90 buildings Large-scale indoor environments (Chang et al.)
HM3D 2021 1K buildings Habitat-scale indoor scans with navigation annotations (Ramakrishnan et al.)
Structured3D 2020 3.5K houses Synthetic indoor scenes with layout and topology labels (Zheng et al.)
Hypersim 2021 461 scenes, 77K images Photorealistic synthetic scenes with material labels (Roberts et al.)
3D-FRONT 2021 18K rooms Professionally designed indoor layouts (Fu et al.)
ProcTHOR 2022 Procedural houses Infinitely scalable simulated interiors (Deitke et al.)
Infinigen 2023 Procedural nature Photorealistic procedural generation of natural worlds (Raistrick et al.)
Infinigen Indoors 2024 Procedural interiors Indoor extension of Infinigen (Raistrick et al.)

General Objects & Props

Geometry Generation

Score Distillation (SDS)

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
DreamFusion 2022 ICLR 2023 Pioneering open-domain text-to-3D via SDS πŸ“„ - 🌐 πŸ“–
Magic3D 2023 CVPR 2023 Coarse-to-fine SDS for higher-resolution detail πŸ“„ - 🌐 πŸ“–
Fantasia3D 2023 ICCV 2023 Disentangled geometry-appearance SDS with DMTet πŸ“„ πŸ’» - πŸ“–
ProlificDreamer 2023 NeurIPS 2023 Variational SDS reducing over-smoothing πŸ“„ πŸ’» - πŸ“–
RichDreamer 2024 CVPR 2024 Normal-depth diffusion prior for stable geometry πŸ“„ πŸ’» - πŸ“–

Multi-View Reconstruction (MV)

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Zero-1-to-3 2023 ICCV 2023 View-conditioned diffusion for novel-view synthesis πŸ“„ πŸ’» - πŸ“–
MVDream 2024 ICML 2024 Multi-view consistent diffusion model πŸ“„ πŸ’» - πŸ“–
Wonder3D 2024 CVPR 2024 Color + normal diffusion for normal-guided recon. πŸ“„ πŸ’» - πŸ“–
SV3D 2024 ECCV 2024 Video diffusion for dense multi-view generation πŸ“„ - 🌐 πŸ“–

GAN-based

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
3D-GAN 2016 NeurIPS 2016 Pioneering voxel-based adversarial 3D generation πŸ“„ - - πŸ“–
Tree-GAN 2019 arXiv 2019 Tree-structured generator for point clouds πŸ“„ - - πŸ“–
SP-GAN 2021 ICCV 2021 Spherical prior for global shape consistency πŸ“„ - - πŸ“–
SDF-StyleGAN 2022 CVPR 2022 StyleGAN adapted for high-resolution SDF fields πŸ“„ - - πŸ“–

VAE / AE

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
AtlasNet 2018 CVPR 2018 Patch-deformation VAE for surface reconstruction πŸ“„ πŸ’» - πŸ“–
TM-Net 2021 arXiv 2021 Joint geometry-texture VAE generation πŸ“„ - - πŸ“–
Michelangelo 2023 NeurIPS 2023 Aligned shape-conditioned VAE with multimodal input πŸ“„ πŸ’» - πŸ“–
CLAY 2024 arXiv 2024 Large-scale VAE + DiT for controllable 3D generation πŸ“„ - - πŸ“–

Direct 3D Diffusion

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
PC-DPM 2021 ICLR 2021 DDPM for point cloud denoising generation πŸ“„ - - πŸ“–
MeshDiffusion 2023 ICLR 2023 Score-based diffusion directly on mesh vertices πŸ“„ πŸ’» - πŸ“–
TetraDiffusion 2024 arXiv 2024 Tetrahedral diffusion for high-resolution topology πŸ“„ - - πŸ“–

Feed-Forward (FF)

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Pixel2Mesh 2018 ECCV 2018 GCN-based mesh deformation from single image πŸ“„ πŸ’» - πŸ“–
LRM 2023 ICLR 2024 Transformer-based large reconstruction model πŸ“„ - 🌐 πŸ“–
TripoSR 2024 arXiv 2024 Distilled feed-forward for sub-second reconstruction πŸ“„ πŸ’» - πŸ“–
GS-LRM 2024 ECCV 2024 Large reconstruction model for 3D Gaussian Splatting πŸ“„ - 🌐 πŸ“–
InstantMesh 2024 arXiv 2024 Multi-view to FlexiCubes mesh with UV πŸ“„ πŸ’» - πŸ“–
LGM 2024 arXiv 2024 Large multi-view Gaussian model for high-resolution 3D content πŸ“„ πŸ’» - πŸ“–
SF3D 2024 arXiv 2024 Joint mesh + UV + PBR material prediction πŸ“„ πŸ’» - πŸ“–
Fast3R 2025 arXiv 2025 Amortized scalable multi-view 3D reconstruction πŸ“„ - - πŸ“–

Latent Generative Models (LGM)

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Shap-E 2023 arXiv 2023 Fast text/image-to-3D via latent diffusion πŸ“„ πŸ’» - πŸ“–
3DShape2VecSet 2023 SIGGRAPH 2023 Unordered vector-set VAE + diffusion πŸ“„ πŸ’» - πŸ“–
LATTICE 2025 arXiv 2025 High-fidelity 3D generation at scale in compact latent space πŸ“„ - - πŸ“–
XCube 2024 CVPR 2024 Hierarchical sparse-voxel latent diffusion πŸ“„ - - πŸ“–
TRELLIS 2025 CVPR 2025 Structured latent (SLAT) with rectified flow πŸ“„ πŸ’» - πŸ“–
TRELLIS.2 2025 arXiv 2025 O-Voxel representation, 4B params, PBR output πŸ“„ πŸ’» - πŸ“–
SparseFlex 2025 arXiv 2025 Sparse isosurface VAE + flow for arbitrary topology πŸ“„ - - πŸ“–
TripoSG 2025 arXiv 2025 VAE + rectified flow DiT for high-fidelity meshes πŸ“„ πŸ’» - πŸ“–
MeshCraft 2025 arXiv 2025 Face-token VAE + flow DiT for parallel mesh gen. πŸ“„ - - πŸ“–

Part-Aware

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
PAGENet 2020 AAAI 2020 Part-aware generation network - - - πŸ“–
SAMPart3D 2024 arXiv 2024 Multi-granularity zero-shot 3D part segmentation - - - πŸ“–
HoloPart 2025 arXiv 2025 Amodal 3D part completion - - - πŸ“–
X-Part 2025 arXiv 2025 Structure-coherent controllable shape decomposition πŸ“„ - - πŸ“–
PartGen 2025 arXiv 2025 Part-level multi-view diffusion generation - - - πŸ“–
PartCrafter 2025 arXiv 2025 Part-wise 3D reconstruction and editing - - - πŸ“–
OmniPart 2025 arXiv 2025 Unified part-aware reconstruction pipeline - - - πŸ“–

Topology Generation

Indirect Methods (Post-hoc Remeshing)

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Instant Meshes 2015 ACM TOG 2015 Field-aligned instant quad/tri remeshing - πŸ’» - πŸ“–
QuadriFlow 2018 SGP 2018 Scalable instant field-aligned quad remeshing πŸ“„ πŸ’» - πŸ“–
NeurCross 2025 arXiv 2025 Neural-guided cross-field remeshing - - - πŸ“–

Direct Methods -- Autoregressive

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
PolyGen 2020 ICML 2020 Pioneering vertex-then-face autoregressive mesh gen. πŸ“„ πŸ’» - πŸ“–
MeshGPT 2024 ICLR 2024 VQ-VAE codebook tokenization for mesh generation πŸ“„ - 🌐 πŸ“–
MeshAnything 2024 arXiv 2024 Shape-conditioned artist mesh extraction πŸ“„ πŸ’» - πŸ“–
MeshAnything V2 2025 arXiv 2025 Adjacent mesh tokenization with improved compression πŸ“„ πŸ’» - πŸ“–
Meshtron 2024 arXiv 2024 Artist-like mesh generation at scale from artist-created data πŸ“„ - - πŸ“–
PivotMesh 2024 arXiv 2024 Coarse-to-fine mesh scaffolding πŸ“„ πŸ’» - πŸ“–
EdgeRunner 2024 arXiv 2024 Hybrid AR-latent mesh generation pipeline πŸ“„ πŸ’» - πŸ“–
QuadGPT 2025 arXiv 2025 Autoregressive quad-mesh generation for edge loops πŸ“„ - - πŸ“–
DeepMesh 2025 ICCV 2025 RL-based preference alignment for artist-quality mesh πŸ“„ πŸ’» - πŸ“–
Mesh-RFT 2025 arXiv 2025 Masked DPO for localized mesh defect correction πŸ“„ - - πŸ“–

Direct Methods -- Diffusion

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
PolyDiff 2023 ICCV 2023 Discrete denoising diffusion over triangle soups πŸ“„ - - πŸ“–
SpaceMesh 2024 arXiv 2024 Continuous halfedge latent diffusion; ultra-fast πŸ“„ - - πŸ“–
MeshCraft 2025 arXiv 2025 Flow-based DiT with face-count control πŸ“„ - - πŸ“–

Appearance Generation

UV Unwrapping

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
xatlas 2018 Open-source Production-baseline automatic UV atlas packer - πŸ’» - πŸ“–
UVAtlas 2023 Open-source Production-baseline atlas generation for UV layout - πŸ’» - πŸ“–
Auto-UV 2025 arXiv 2025 Learned seam prediction for UV unwrapping - - - πŸ“–
Flatten Anything 2024 arXiv 2024 Unsupervised cycle-consistent UV mapping - - - πŸ“–
FlexPara 2025 arXiv 2025 Flexible unsupervised UV parameterization πŸ“„ - - πŸ“–
PartUV 2025 arXiv 2025 Semantic chart-aligned UV partitioning - - - πŸ“–
ArtUV 2025 arXiv 2025 Artist-style UV packing and layout πŸ“„ - - πŸ“–
SeamCrafter 2025 arXiv 2025 Seam preference optimization for UV quality πŸ“„ - - πŸ“–
Hunyuan3D Studio 2025 arXiv 2025 End-to-end game-ready asset pipeline with integrated UV construction πŸ“„ - - πŸ“–

Texture & PBR Material Generation

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
TEXTure 2023 SIGGRAPH 2023 Iterative text-guided texture painting πŸ“„ πŸ’» - πŸ“–
Text2Tex 2023 ICCV 2023 Progressive inpainting for mesh texturing πŸ“„ πŸ’» - πŸ“–
TexFusion 2023 arXiv 2023 Cross-view aggregated texture fusion πŸ“„ - - πŸ“–
Paint3D 2024 arXiv 2024 Illumination-free texture diffusion for PBR πŸ“„ πŸ’» - πŸ“–
FlashTex 2024 arXiv 2024 Fast text-to-texture generation πŸ“„ - - πŸ“–
TexGen 2024 arXiv 2024 Feed-forward UV-space texture diffusion - - - πŸ“–
MVPaint 2025 arXiv 2025 Multi-view consistent texture painting πŸ“„ - - πŸ“–
MaterialMVP 2025 ICCV 2025 Illumination-invariant multi-view PBR diffusion - - - πŸ“–
MaterialAnything 2024 arXiv 2024 PBR material decomposition as first-class objective πŸ“„ - - πŸ“–
3DTopia-XL 2024 arXiv 2024 Primitive diffusion for high-quality 3D assets with joint UV/PBR objectives πŸ“„ πŸ’» - πŸ“–
Meta 3D AssetGen 2024 arXiv 2024 Unified UV + geometry + PBR material pipeline πŸ“„ - - πŸ“–
PBR3DGen 2025 arXiv 2025 VLM-guided mesh generation with PBR materials πŸ“„ - - πŸ“–

Characters & Avatars

Structural Priors

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
SMPL 2015 SIGGRAPH Asia 2015 Skinned multi-person linear body model πŸ“„ - - πŸ“–
SMPL-X 2019 CVPR 2019 Expressive body + hands + face parametric model - - - πŸ“–
FLAME 2017 SIGGRAPH Asia 2017 Learned head model with expression blendshapes - - - πŸ“–

Full-Body Synthesis

Parametric Template

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Tex2Shape 2019 ICCV 2019 UV-space displacement prediction on SMPL - - - πŸ“–
CAPE 2020 CVPR 2020 Pose-dependent clothing offsets on body mesh - - - πŸ“–
ExPose 2020 ECCV 2020 Monocular body + hands + face estimation - - - πŸ“–
STAR 2020 ECCV 2020 Sparse parametric SMPL variant - - - πŸ“–
HybrIK 2021 CVPR 2021 Hybrid analytical-regressive IK for body mesh - - - πŸ“–

Implicit / Hybrid

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
PIFu 2019 ICCV 2019 Pixel-aligned implicit function for clothed humans - - - πŸ“–
ARCH 2020 CVPR 2020 Canonical implicit field with SMPL-guided rigging - - - πŸ“–
PIFuHD 2020 CVPR 2020 Multi-level implicit for high-res human recon. - - - πŸ“–
PaMIR 2021 TPAMI 2021 Parametric body model inside implicit recon. - - - πŸ“–
SMPLicit 2021 CVPR 2021 Implicit clothing conditioned on SMPL parameters πŸ“„ πŸ’» - πŸ“–
ICON 2022 CVPR 2022 Normal-guided implicit body with SMPL - - - πŸ“–
gDNA 2022 ECCV 2022 Generative implicit model for diverse humans - - - πŸ“–
ECON 2023 CVPR 2023 Implicit + explicit mesh hybrid reconstruction - - - πŸ“–
S3F 2023 ICCV 2023 Structured 3D features with SMPL semi-supervision - - - πŸ“–

GAN / Diffusion Generative

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
StylePeople 2021 arXiv 2021 GAN-based clothed mesh synthesis - - - πŸ“–
AvatarGen 2022 arXiv 2022 SDF + tri-plane GAN for 3D avatars - - - πŸ“–
AvatarCLIP 2022 SIGGRAPH 2022 CLIP-guided text-to-avatar generation πŸ“„ πŸ’» - πŸ“–
Get3DHuman 2023 arXiv 2023 Tri-plane/SDF GAN for full-body humans πŸ“„ πŸ’» - πŸ“–
GETAvatar 2023 NeurIPS 2023 GAN + SMPL for animatable textured mesh - - - πŸ“–
AvatarCraft 2023 arXiv 2023 SDS-based NeRF-to-mesh avatar generation - - - πŸ“–
DreamHuman 2023 arXiv 2023 SDS + imGHUM body prior for text-to-human πŸ“„ - - πŸ“–
ChuPa 2023 arXiv 2023 2D diffusion on SMPL with displacement - - - πŸ“–
DreamAvatar 2024 arXiv 2024 SDS + SMPL-guided NeRF avatar synthesis - - - πŸ“–
Morphable Diffusion 2024 CVPR 2024 3D-consistent diffusion for single-image avatar creation πŸ“„ - - πŸ“–
SiTH 2024 CVPR 2024 Single-view textured human reconstruction with image-conditioned diffusion πŸ“„ - - πŸ“–
TADA! 2024 CVPR 2024 SMPL-X + texture with LBS-ready rigging πŸ“„ πŸ’» - πŸ“–

Feed-Forward / Real-Time

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
InstantAvatar 2023 CVPR 2023 Fast neural field from monocular video - - - πŸ“–
SHERF 2023 arXiv 2023 Canonical-prior NeRF for generalizable humans - - - πŸ“–
LRM 2023 ICLR 2024 Feed-forward large reconstruction model adapted to human body synthesis πŸ“„ - 🌐 πŸ“–
Human GS 2024 arXiv 2024 Canonical 3DGS with skinning from multi-view - - - πŸ“–
HUGS 2024 CVPR 2024 3DGS + SMPL for real-time avatar playback - - - πŸ“–
3DGS-Avatar 2024 arXiv 2024 Deformable 3DGS bound to skinning weights πŸ“„ πŸ’» - πŸ“–
LHM 2025 arXiv 2025 Dense Gaussians on SMPL; animatable in seconds - - - πŸ“–
OmniAvatar 2025 arXiv 2025 Video diffusion for temporally coherent avatars - - - πŸ“–

Head & Face Synthesis

Morphable + Neural

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
i3DMM 2021 arXiv 2021 Implicit SDF-based 3D morphable model - - - πŸ“–
NerFace 2021 arXiv 2021 NeRF with expression-conditioned deformation - - - πŸ“–
EG3D 2022 CVPR 2022 Efficient tri-plane GAN for 3D face generation - - - πŸ“–
NPHM 2023 arXiv 2023 Dual-SDF for identity + expression disentanglement - - - πŸ“–
Next3D 2023 CVPR 2023 Tri-plane + texture rasterization with FLAME - - - πŸ“–
PanoHead 2023 CVPR 2023 Depth-aware tri-grid for full 360-degree heads - - - πŸ“–
RODIN 2023 arXiv 2023 Diffusion on tri-plane for novel-ID head generation - - - πŸ“–
HeadSculpt 2023 arXiv 2023 SDS NeRF with SMPL-X prior for head sculpting - - - πŸ“–

Mesh-Anchored Gaussians

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
GaussianAvatars 2024 CVPR 2024 3DGS bound to FLAME triangles for animation - - - πŸ“–
FlashAvatar 2024 arXiv 2024 >300 FPS 3DGS + FLAME; production-ready - - - πŸ“–
MonoGaussianAvatar 2024 arXiv 2024 Monocular-video 3DGS on FLAME mesh - - - πŸ“–
RGCA (Relightable) 2024 arXiv 2024 Full PBR 3DGS decomposition for relighting - - - πŸ“–

Feed-Forward Reconstruction

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
GAGAvatar 2024 arXiv 2024 Generalizable 3DGS from single image with FLAME - - - πŸ“–
Arc2Avatar 2025 arXiv 2025 Identity-guided single-image 3DGS head recon. - - - πŸ“–
HRAvatar 2025 arXiv 2025 PBR 3DGS with roughness + Fresnel from mono video - - - πŸ“–
LAM 2025 arXiv 2025 Large Avatar Model; 280 FPS, LBS-compatible - - - πŸ“–
Avat3r 2025 arXiv 2025 Sparse-view canonical 3DGS via ViT - - - πŸ“–

Rendering & Animation

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
SadTalker 2023 CVPR 2023 Audio-to-FLAME coefficients for talking-head video - - - πŸ“–
HunyuanVideo-Avatar 2025 arXiv 2025 High-fidelity audio-driven human animation for multiple characters πŸ“„ - - πŸ“–
TexTalker 2025 arXiv 2025 Audio-sync wrinkle maps + geometric deformation - - - πŸ“–

Rigging & Skinning

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
RigNet 2020 SIGGRAPH 2020 End-to-end GNN skeleton + skinning prediction - - - πŸ“–
SkinningNet 2022 arXiv 2022 Two-stream GNN for heterogeneous skeletal topologies - - - πŸ“–
DeePSD 2021 arXiv 2021 Unsupervised physics-based garment skinning - - - πŸ“–

Note: TADA!, ChuPa, LAM, and HRAvatar also include rigging capabilities -- see above.


Scenes & Environments

Layout Generation

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
ATISS 2021 NeurIPS 2021 Autoregressive transformer for room layouts πŸ“„ πŸ’» - πŸ“–
ProcTHOR 2022 NeurIPS 2022 Procedural interactive houses for embodied AI - πŸ’» 🌐 πŸ“–
Pose2Room 2022 arXiv 2022 Activity-driven affordance-aware room layout - - - πŸ“–
DiffuScene 2024 arXiv 2024 Diffusion + retrieval for furnished indoor scenes πŸ“„ πŸ’» - πŸ“–
Holodeck 2024 CVPR 2024 LLM-planned embodied environment generation - - - πŸ“–
LayoutGPT 2023 arXiv 2023 LLM-generated indoor layouts from text - - - πŸ“–
LLplace 2024 arXiv 2024 Dialogue-driven interactive layout editing πŸ“„ - - πŸ“–
CityCraft 2024 arXiv 2024 Language-guided city-scale layout generation πŸ“„ - - πŸ“–

Scene Population & Asset Grounding

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
MIME 2023 arXiv 2023 Human-motion-informed object placement - - - πŸ“–
AnyHome 2023 arXiv 2023 Open-vocabulary text-to-house scene generation πŸ“„ - - πŸ“–
Open-Universe 2024 arXiv 2024 LLM programs + solver for open-vocabulary scenes πŸ“„ - - πŸ“–
SceneCraft 2024 arXiv 2024 Blender code agent for executable scene scripts - - - πŸ“–
PhyScene 2024 arXiv 2024 Physics-guided diffusion for interactable scenes - - - πŸ“–
UnrealLLM 2025 arXiv 2025 Unreal Engine PCG agents from language - - - πŸ“–
Layout2Scene 2025 arXiv 2025 Layout-guided diffusion for holistic scenes πŸ“„ - - πŸ“–
3D-GPT 2023 arXiv 2023 Procedural modeling as language-conditioned programs πŸ“„ πŸ’» - πŸ“–
PhysGen3D 2025 arXiv 2025 Miniature interactive worlds with physics simulation - - - πŸ“–

World-Scale Generation

Method Year Venue Highlight πŸ“„ πŸ’» 🌐 πŸ“–
Text2Light 2022 arXiv 2022 Text-conditioned HDR panorama for skybox/lighting πŸ“„ πŸ’» - πŸ“–
Text2Room 2023 arXiv 2023 2D diffusion lifted to textured room meshes πŸ“„ πŸ’» - πŸ“–
Infinigen 2023 CVPR 2023 Photorealistic procedural natural world generation - - - πŸ“–
CityDreamer 2024 arXiv 2024 Unbounded urban synthesis with stuff + thing fields πŸ“„ πŸ’» - πŸ“–
Infinigen Indoors 2024 arXiv 2024 Photorealistic procedural indoor worlds - - - πŸ“–
LayerPano3D 2025 arXiv 2025 Layered panorama to explorable 3DGS scene - - - πŸ“–
WorldCraft 2025 arXiv 2025 LLM-agentic world editing and customization πŸ“„ - - πŸ“–

Evaluation & Benchmarks

The survey identifies several complementary evaluation dimensions for production-ready 3D generation:

Dimension Metrics
Geometric Fidelity Chamfer Distance (CD), Earth Mover's Distance (EMD), F-Score, Normal Consistency, Coverage (COV), Minimum Matching Distance (MMD), 1-NNA
Appearance Quality PSNR, SSIM, LPIPS, FID, KID, CLIP Score, CLIP R-Precision
PBR / Relighting Relighting consistency, albedo/roughness/metallic separation quality, paper-specific material decomposition tests
Asset Usability UV stretch and angular distortion, seam visibility, chart packing efficiency, overlap detection, rig smoothness, retargeting success, engine import success
Topology Readiness Manifoldness, watertightness, genus correctness, quad ratio, edge-flow alignment, collision-mesh quality
Scene-Level Physical plausibility, interpenetration, NavMesh connectivity, navigation success rate, affordance compatibility, A/B preference, Likert ratings

A key finding of this survey is that existing benchmarks systematically overestimate deployment readiness by focusing on geometric and appearance metrics while neglecting topology, UV/PBR, engine import, and other asset usability criteria required for interactive applications.


Industry & Companies

Company Key Product Type Link
Tripo AI Tripo V2.5 Closed tripo3d.ai
Tencent Hunyuan3D Open + Closed 3d.hunyuan.tencent.com
ByteDance MVDream Open -
Meshy AI Meshy 5 Closed meshy.ai
Deemos Rodin Gen 1.5 Closed hyperhuman.deemos.com
DreamTech - Closed dreamtech.com
Luma AI Genie Closed lumalabs.ai
CSM AI - Closed csm.ai
Stability AI SF3D Open stability.ai
NVIDIA Edify 3D Closed build.nvidia.com
SUDO AI - Closed sudo.ai

Citation

If you find this survey useful, please cite our paper:

@article{wu2026visual,
  title={From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation},
  author={Wu, Jiafeng and Lou, Zhuofan and Liu, Jian and Du, Dazhao and Guo, Chunchao and Guo, Song},
  journal={arXiv preprint arXiv:2604.23629},
  year={2026}
}

If you also use resources from the v1 collection, please additionally cite:

@article{liu2024comprehensive,
  title={A Comprehensive Survey on 3D Content Generation},
  author={Liu, Jian and Huang, Xiaoshui and Huang, Tianyu and Chen, Lu and Hou, Yuenan and Tang, Shixiang and Liu, Ziwei and Ouyang, Wanli and Zuo, Wangmeng and Jiang, Junjun and others},
  journal={arXiv preprint arXiv:2402.01166},
  year={2024}
}

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Note: Pull requests should target the v2 branch. The main branch preserves the original v1 awesome list.


Acknowledgments

This work was supported by The Hong Kong University of Science and Technology and Tencent.


v1 Paper Collection

The original awesome list curated is preserved on the main branch. It contains a broader collection of AIGC 3D papers organized by topic without the production-pipeline focus of v2.


Star History

Star History Chart

About

A curated list of awesome AIGC 3D papers

Resources

Contributing

Stars

788 stars

Watchers

27 watching

Forks

Releases

Packages

Contributors

Languages