Awesome-Text-to-3D

InstantHMR: Real-Time Human Mesh Recovery on Your Phone, Mohamed Adjel et al., Arxiv 2026 | citation | site | code | ▲ citation count: unavailable

Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D, Gaige Wang et al., Arxiv 2026 | citation | site | code | ▲ citation count: unavailable

Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction, Prakhar Kaushik et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

CityLift: Compositional 3D Urban Generation from a Single Image, Haoran Gong et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction, Ziang Zhang et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction, Ranran Huang et al., Arxiv 2026 | citation | site | code (coming soon) | ▲ citation count: 0

TriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene Generation, Yun Wang et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

GenIA: Generative Reconstruction with Test-Time Input Alignment, Stefano Esposito et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

NeRFifyMesh: Optimizing Neural Radiance Fields from Textured Meshes for Robotics Scene Building, Nillan Nimal et al., IROS 2026 | citation | site | code | ▲ citation count: 0

NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis, Ramil Khafizov et al., NeurIPS 2026 | citation | site | code | ▲ citation count: 0

T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images, Atsuhiro Noguchi et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Feedforward Novel View Synthesis for Heterogeneous Cameras, Meng Wei et al., NeurIPS 2026 | citation | site | code | ▲ citation count: 0

VCURF: Virtual Camera-based Uncertainty of Radiance Fields, Liyan Chen et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

EffGS: Efficient and High-Fidelity Gaussian Splatting, Changbai Li et al., Arxiv 2026 | citation | site | code (coming soon) | ▲ citation count: 0

LEGO-Anything: Coding Agents for 3D Scene Reconstruction, Xirui Li et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Spackle: Completing Large View Single Image NVS with Adaptive Gaussians, Xuanzhi Liu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera–LiDAR Novel View Synthesis, Yang Zhou et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

OceanXL: Large-scale Underwater 3D Gaussian Splatting via Block Partitioning and Adaptive Pruning, Haoran Wang et al., SIGGRAPH Asia 2026 | citation | site | code | ▲ citation count: 0

EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion, Ilias Mitsouras et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction, Yang-Tian Sun et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization, Yibin Zhao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructions, Rinto Yagawa et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis, Wenyu Li et al., ACM MM 2026 | citation | site | code | ▲ citation count: 0

3D Point Splatting for mmWave Radar Novel View Synthesis, Adnan Armouti et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation, Jiarui Liu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

StreetDiff: Multi-view Street Scenes Generation via Cross-view Consistent Multi-view Stable Diffusion with Structure Prompts, Qi Zhang et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

View-Structured Conformal Prediction for 3D Gaussian Splatting, Junzheng Chu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

AnimalLift: Reconstructing Animatable 3D Animals from a Single Image by Learning Canonical Shape, Texture, and Fur Maps, Chunyi Sun et al., SIGGRAPH Asia 2026 | citation | site | code | ▲ citation count: 0

FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute, Hongchi Xia et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning, Muyu Xu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Reflection-aware Generative Novel View Synthesis, GeonU Kim et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

Compact Neural Appearance Models for Efficient Gaussian Splatting, Florian Hahlbohm et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations, Denis M. Akola et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting, Qian Wang et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation, Xinyu Wang et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding, Boyu Cai et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing, Haonan Zhou et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views, Giuseppe Stracquadanio et al., ECCV 2026 | citation | site | code | ▲ citation count: 1

Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots, Yongho Kim et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Luce: Relightable Gaussians for 3D Asset Generation, Mayank Singh et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

SceneReGen: Generative Reconstruction of 3D Scenes from a Single Image, Zefan Tian et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation, Yumeng He et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

ExMesh++: From Multi-View Images to Relightable UV-PBR Mesh Assets via Topology-Adaptive Reconstruction and Decomposition, Chuanjin Fan et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors, Khiem Vuong et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

TopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction, Chuanjin Fan et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion, Bowen Cui et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Control, Ava Pun et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

View-Adaptive Renderer for View-Consistent 2D-to-3D Generation, U-Chae Jun et al., Multimedia Systems 2026 | citation | site | code | ▲ citation count: 0

FlexSplat: Flexible Feed-Forward 3D Gaussian Splatting without Point Cloud Correspondence, Amir Sabbaghziarani et al., BMVC 2026 | citation | site | code | ▲ citation count: 0

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding, Lucy Lin et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing, Junliang Ye et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Meshy T2: Fast Native Mesh Generation with Flow Matching, Jiale Xu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 1

Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to Pipeline, Qisen Wang et al., IJCV 2026 | citation | site | code | ▲ citation count: 0

Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation, Jian Huang et al., IROS 2026 | citation | site | code | ▲ citation count: 0

G$^2$SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction, Dasong Gao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency, Andreas Meuleman et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos, Ziren Gong et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation, Eungjune Shim et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects, Tahmina Khanam et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning, Yuan Xiao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets, Xian Li et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Glob3R: Global Structure-from-Motion with 3D Foundation Models, Junyuan Deng et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

StereoSplat+: Feed-Forward Stereo Gaussian Splatting with Diffusion-Assisted Progressive Inference, Zihua Liu et al., IROS 2026 | citation | site | code | ▲ citation count: 0

Nexus: Native Mesh Generation with Diffusion, Hanxiao Wang et al., Arxiv 2026 | citation | site | code | ▲ citation count: 2

PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation, Duy Cao et al., ECCV 2026 | citation | site | code | ▲ citation count: 0

Printing the Underdetermined: Materializing Multi-solutionness in Figurative Paintings, Yutao Ming et al., PACMCGIT 2026 | citation | site | code | ▲ citation count: 0

UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image, Mohamed El Amine Boudjoghra et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views, Mijin Yoo et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design, Yiyun Fei et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling, Zhijie Zheng et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models, Guangzhao He et al., Arxiv 2026 | citation | site | code | ▲ citation count: 1

VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching, Tuan Duc Ngo et al., Arxiv 2026 | citation | site | code | ▲ citation count: 1

S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields, Deniz Sayin Mercadier et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image, Xiaoxuan Ma et al., Arxiv 2026 | citation | site | code | ▲ citation count: 2

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction, Katharina Schmid et al., Arxiv 2026 | citation | site | code | ▲ citation count: 1

ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation, Hanxiao Sun et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects, Ziang Cao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation, Matt Zhou et al., Arxiv 2026 | citation | site | code | ▲ citation count: 4

DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion, Yuhan Ping et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation, Baicheng Li et al., Arxiv 2026 | citation | site | code | ▲ citation count: 3

RelaxFlow: Text-Driven Amodal 3D Generation, Jiayin Zhu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-turn RL, Yang Zhao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming, Jisheng Chu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

GeoDiff3D: Self-Supervised 3D Scene Generation with Geometry-Constrained 2D Diffusion Guidance, Haozhi Zhu et al., Arxiv 2026 | citation | site | code | ▲ citation count: 0

AnchoredDream: Zero-Shot 360{\deg} Indoor Scene Generation from a Single View via Geometric Grounding, Runmao Yao et al., Arxiv 2026 | citation | site | code | ▲ citation count: 1

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning, Shaofeng Yin et al., Arxiv 2026 | citation | site | code | ▲ citation count: 6

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement, Tanghui Jia et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Native and Compact Structured Latents for 3D Generation, Jianfeng Xiang et al., Arxiv 2025 | citation | site | code | ▲ citation count: 30

Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation, Yiwen Tang et al., Arxiv 2025 | citation | site | code | ▲ citation count: 2

MeshRipple: Structured Autoregressive Generation of Artist-Meshes, Junkai Lin et al., Arxiv 2025 | citation | site | code | ▲ citation count: 1

SAM 3D: 3Dfy Anything in Images, SAM 3D Team et al., Arxiv 2025 | citation | site | code | ▲ citation count: 19

FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion, Chuhao Chen et al., Arxiv 2025 | citation | site | code | ▲ citation count: 5

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets, Jiashi Feng et al., Arxiv 2025 | citation | site | code | ▲ citation count: 2

Blended Point Cloud Diffusion for Localized Text-guided Shape Editing}, Etai Sella et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

FlashWorld: High-quality 3D Scene Generation within Seconds, Jinyang Li et al., Arxiv 2025 | citation | site | code | ▲ citation count: 5

Wonder3D++: Cross-Domain Diffusion for High-Fidelity 3D Generation From a Single Image, Yang, Yuxiao et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation, Sherwin Bahmani et al., Arxiv 2025 | citation | site | code | ▲ citation count: 6

Dream3DAvatar: Text-Controlled 3D Avatar Reconstruction from a Single Image, Gaofeng Liu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation, Biwen Lei et al., Arxiv 2025 | citation | site | code | ▲ citation count: 4

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds, Bingquan Dai et al., Arxiv 2025 | citation | site | code | ▲ citation count: 2

LL3M: Large Language 3D Modelers, Sining Lu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 2

BrepDiff: Single-stage B-rep Diffusion Model, Mingi Lee et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

PhysX-3D: Physical-Grounded 3D Asset Generation, Giang Cao et al., Arxiv 2025 | citation | site | code | ▲ citation count: 7

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS, Wanhua Li et al., Arxiv 2025 | citation | site | code | ▲ citation count: 1

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion, Fangfu Liu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy, Yuhao Liu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion, Yansong Qu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 3

Consistent Zero-shot 3D Texture Synthesis Using Geometry-aware Diffusion and Temporal Video Models, Donggoo Kang et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence, Xinjie Wang et al., Arxiv 2025 | citation | site | code | ▲ citation count: 3

Convolutional Neural Shading for High-Quality 3D Reconstruction from Multi-View Images, Juheon Hwang et al., Multimedia Systems 2025 | citation | site | code | ▲ citation count: 0

ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding, Junliang Ye et al., Arxiv 2023 | citation | site | code | ▲ citation count: 7

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention, Shuang Wu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 15

Constructing a 3D Town from a Single Image, Kaizhi Zheng et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits, Nail Ibrahimli et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets, Weiyu Li et al., Arxiv 2025 | citation | site | code | ▲ citation count: 9

Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splatting, Feng Yang et al., Arxiv 2025 | citation | site | code | ▲ citation count: 1

Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis, Michal Geyer et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation, Michal Geyer et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

TesserAct: Learning 4D Embodied World Models, Haoyu Zhen et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Art3D: Training-Free 3D Generation from Flat-Colored Illustration, Xiaoyan Cong et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Generating 360° Video is What You Need For a 3D Scene, Zhaoyang Zhang et al., SIGGRAPH Asia 2025 | citation | site | code | ▲ citation count: 0

ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image, Tianyi Gong et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs, Xianglong He et al., Arxiv 2025 | citation | site | code | ▲ citation count: 2

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data, Zhiyuan Ma et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

Stable Virtual Camera: Generative View Synthesis with Diffusion Models, Jensen Zhou et al., Arxiv 2025 | citation | site | code | ▲ citation count: 10

Bolt3D: Generating 3D Scenes in Seconds, Stanislaw Szymanowicz et al., Arxiv 2025 | citation | site | code | ▲ citation count: 12

Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images, Tianhao Wu et al., Arxiv 2025 | citation | site | code | ▲ citation count: 7

PBR3DGen: A VLM-guided Mesh Generation with High-quality PBR Texture, Xiaokang Wei et al., Arxiv 2025 | citation | site | code | ▲ citation count: 0

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior, Zichen Tang et al.,