Stars
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page conte…
[NeurIPS 2024] Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Roblox Foundation Model for 3D Intelligence
Solve Visual Understanding with Reinforced VLMs
A PyTorch Library for Accelerating 3D Deep Learning Research
Some simple Blender scripts for rendering paper figures
🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!
[NeurIPS 2024] Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering
VMamba: Visual State Space Models，code is based on mamba
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
An open-source impl. of Large Reconstruction Models
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.