Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

PyTorch code and models for the DINOv2 self-supervised learning method.

This is the official code for the paper Tailor3D

[SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Efficient Part-level 3D Object Generation via Dual Volume Packing

Official implementation of Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering (ICLR 2025)

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Official implementation of "WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction"

Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"

SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.

Differentiable Vector Graphics Rasterization

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.

Official implementation of 3Doodle: Compact Abstraction of Objects with 3D Strokes (SIGGRAPH 24', Journal track)

[CVPR'24] 3D Neural Edge Reconstruction

3D Edge Mapping using Edge-Specialized Gaussian Splatting

📚 A collection of papers about Sketch Synthesis (Generation).

📚 A collection of sketch based application papers.

Public code release for our SIGGRAPH 2019 paper "PlanIT: Planning and Instantiating Indoor Scenes with Relation Graph and Spatial Prior Networks"

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

The official implementation of ACM Multimedia 2024 paper "PlacidDreamer: Advancing Harmony in Text-to-3D Generation".

LPIPS metric. pip install lpips

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"