The work creates the first dataset and baseline for generating emission textures on 3D objects to reproduce glowing materials from input images.
hub
Step1x-3d: Towards high-fidelity and con- trollable generation of textured 3d assets
25 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
25
Pith papers citing it
1
external citations · Pith
abstract
While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation. To this end, we present Step1X-3D, an open framework addressing these challenges through: (1) a rigorous data curation pipeline processing >5M assets to create a 2M high-quality dataset with standardized geometric and textural properties; (2) a two-stage 3D-native architecture combining a hybrid VAE-DiT geometry generator with an diffusion-based texture synthesis module; and (3) the full open-source release of models, training code, and adaptation modules. For geometry generation, the hybrid VAE-DiT component produces TSDF representations by employing perceiver-based latent encoding with sharp edge sampling for detail preservation. The diffusion-based texture synthesis module then ensures cross-view consistency through geometric conditioning and latent-space synchronization. Benchmark results demonstrate state-of-the-art performance that exceeds existing open-source methods, while also achieving competitive quality with proprietary solutions. Notably, the framework uniquely bridges the 2D and 3D generation paradigms by supporting direct transfer of 2D control techniques~(e.g., LoRA) to 3D synthesis. By simultaneously advancing data quality, algorithmic fidelity, and reproducibility, Step1X-3D aims to establish new standards for open research in controllable 3D asset generation.
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
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-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI and Gen3DSR while keeping diffusion efficiency.
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
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.
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
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.
A training-free Spatio-Temporal Attention Chain framework accelerates 4D mesh generation 13x, improves quality, scales to 16x longer videos, and supports downstream tracking and camera estimation.
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.
BVE framework enables text-guided 3D editing beyond voxel limits by combining self-constructed data, lightweight semantic injection, and annotation-free masking to preserve local invariance.
Scaling transformer context with sparse attention and 3D-aware block routing improves feed-forward 3D reconstruction and inverse rendering, closing much of the quality gap with dense-view optimization.
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.
A unified generative pipeline produces cross-simulator, affordance-annotated, task-conditioned 3D worlds that support online robot policy training and real-robot transfer.
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.
MeshWeaver uses sparse-voxel guidance for autoregressive surface weaving to achieve 18% compression and generate up to 16K-face meshes with improved fidelity.
Sketch2Motion is a diffusion-guided skeleton optimization framework that generates text-driven 3D animations from 2D sketches for biped, quadruped, and other articulated characters.
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.
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
DataEvolver introduces a reusable framework with generation-time self-correction and validation-time self-expansion loops that improves visual datasets, shown to outperform baselines on an object-rotation task.
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.
CG-MLLM is a multimodal LLM using a Mixture-of-Transformer architecture with separate TokenAR and BlockAR components integrated with a pre-trained vision-language backbone and 3D VAE to enable 3D captioning and high-fidelity generation.
citing papers explorer
-
Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generation
The work creates the first dataset and baseline for generating emission textures on 3D objects to reproduce glowing materials from input images.
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
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.
-
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
3D-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI and Gen3DSR while keeping diffusion efficiency.
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
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.
-
Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
-
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
-
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.
-
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
A training-free Spatio-Temporal Attention Chain framework accelerates 4D mesh generation 13x, improves quality, scales to 16x longer videos, and supports downstream tracking and camera estimation.
-
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.
-
Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data
BVE framework enables text-guided 3D editing beyond voxel limits by combining self-constructed data, lightweight semantic injection, and annotation-free masking to preserve local invariance.
-
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
Scaling transformer context with sparse attention and 3D-aware block routing improves feed-forward 3D reconstruction and inverse rendering, closing much of the quality gap with dense-view optimization.
-
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.
-
EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
A unified generative pipeline produces cross-simulator, affordance-annotated, task-conditioned 3D worlds that support online robot policy training and real-robot transfer.
-
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.
-
MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
MeshWeaver uses sparse-voxel guidance for autoregressive surface weaving to achieve 18% compression and generate up to 16K-face meshes with improved fidelity.
-
Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization
Sketch2Motion is a diffusion-guided skeleton optimization framework that generates text-driven 3D animations from 2D sketches for biped, quadruped, and other articulated characters.
-
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.
-
WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
-
DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents
DataEvolver introduces a reusable framework with generation-time self-correction and validation-time self-expansion loops that improves visual datasets, shown to outperform baselines on an object-rotation task.
-
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.
-
CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
CG-MLLM is a multimodal LLM using a Mixture-of-Transformer architecture with separate TokenAR and BlockAR components integrated with a pre-trained vision-language backbone and 3D VAE to enable 3D captioning and high-fidelity generation.
-
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Hunyuan3D 2.1 is a two-part system with DiT for shape generation and Paint for texture synthesis that produces high-fidelity 3D assets with PBR materials.