[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Gemma open-weight LLM library, from Google DeepMind

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

A PyTorch native platform for training generative AI models

(NeurIPS 2024) LiT: Unifying LiDAR "Languages" with LiDAR Translator

The Abstraction and Reasoning Corpus

[NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D

Web-based 3D visualization in Python

A generative world for general-purpose robotics & embodied AI learning.

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

[CVPR 2024] Probing the 3D Awareness of Visual Foundation Models

[SIGGRAPH'24] Implementations for "High-quality Surface Reconstruction using Gaussian Surfels".

Vector (and Scalar) Quantization, in Pytorch

Grounding Image Matching in 3D with MASt3R

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Efficient vision foundation models for high-resolution generation and perception.

🎥 Command line media player

High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)

PyTorch implementation of normalizing flow models

Gaussian mixture models in PyTorch.

[3DV 2026] TRASE: Tracking-free 4D Segmentation and Editing

VisionLLM Series