MapAnything: Universal Feed-Forward Metric 3D Reconstruction

WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency

Native and Compact Structured Latents for 3D Generation

(SIGGRAPH Asia 2025) Improved SDS algorithm for 4D generation

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Training code for "Radiance Meshes for Volumetric Reconstruction".

Echo-4o

Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

SONIC: Spectral Optimization of Noise for Inpainting with Consistency

Official inference repo for FLUX.2 models

Official code implementation of paper "Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting".

HunyuanVideo-1.5: A leading lightweight video generation model

SAM 3D Objects

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Depth Anything 3

[CVPR2025]Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

Official Torch/CUDA Implementation of Faithful Contouring

Interactive visualizations of the geometric intuition behind diffusion models.

Fast and Universal 3D reconstruction model for versatile tasks

Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

[arXiv 2025] Generative View Stitching

Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"

https://little-misfit.github.io/GRAG-Image-Editing/

Kimi K2 is the large language model series developed by Moonshot AI team

[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation