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.
hub Mixed citations
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Mixed citation behavior. Most common role is background (67%).
69
Pith papers citing it
Background
67% of classified citations
abstract
We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
hub tools
citation-role summary
background 9
baseline 1
method 1
other 1
citation-polarity summary
representative citing papers
WarpHammer densifies scene warps with 3D object priors from generative models and fuses pose-unknown auxiliary views via multi-view geometry to enable stable extreme novel view synthesis.
UnfoldArt uses a two-round structured debate between high-level semantic agents and low-level parameter agents, grounded in generated video, to infer articulation and reconstruct full articulated 3D objects including occluded geometry from text or image inputs.
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.
CelloCut formulates watertight remeshing as binary labeling on a Delaunay tetrahedral partition solved by graph-cut minimization with one-sided constraints to guarantee volumetrically consistent solids.
A two-stage autoregressive framework centered on BoxMesh recovers parametric sewing patterns from 3D garment surfaces, claiming state-of-the-art results on benchmarks and generalization to real scans and single-view images.
PerpetualWonder introduces a closed-loop generative simulator with a unified physical-visual representation for long-horizon action-conditioned 4D scene generation from one image.
ATATA enables fast joint inference of structurally aligned pairs using Rectified Flow models via segment transport, improving state-of-the-art for image and video generation while matching 3D quality at much higher speed.
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
OmniFit uses a conditional transformer decoder to predict dense body landmarks from multi-modal inputs for scale-agnostic SMPL-X fitting, outperforming prior methods by 57-81% and reaching millimeter accuracy on CAPE and 4D-DRESS benchmarks.
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 video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
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.
GenLCA enables scalable training of a 3D diffusion model for photorealistic, animatable full-body avatars by tokenizing large-scale real-world videos with a pretrained reconstructor and applying visibility-aware diffusion training to handle partial observations.
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.
PointSplat infers compact Gaussian splats directly in 3D space from input point sets via ray casting and Point-Image Transformer to reduce inter-view redundancy and improve novel-view quality for humans.
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.
DualBrep encodes B-rep models as dual scalar fields (SDF geometry + UDF topology) compressed into a shared latent space for flow-matching generation and neural B-rep extraction.
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.
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.
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++ 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.
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.
citing papers explorer
-
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.