[AAAI 2026] Multi-Step Deformable Gaussian Splatting for Dynamic Scene Rendering

[ICLR 2026] ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting

Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Enjoy the magic of Diffusion models!

[Siggraph Asia 25] SS4D: Native 4D Generative Model via Structured Spacetime Latents

[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation

[SIGGRAPH Asia 25] Official code for Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction

Official code release for the paper: Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fields

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)

This repository contains implementations and illustrative code to accompany DeepMind publications

Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

A terminal based graphical activity monitor inspired by gtop and vtop

A Cross-Platform Backend for High-Performance Sparse Convolutions

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

[AAAI 2026] 4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Native and Compact Structured Latents for 3D Generation

Official Implementation of "DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning"

[ICCV 2023 Oral] Official Implementation of "Denoising Diffusion Autoencoders are Unified Self-supervised Learners"

Source code for ICCV 2025 paper "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"