NVIDIA Spatial Intelligence Lab (SIL) ORG

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

Ray tracing and hybrid rasterization of Gaussian particles

ViPE: Video Pose Engine for Geometric 3D Perception

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Project Lyra: Open Generative 3D World Models

Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

No description.

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

Unifying 3D Mesh Generation with Language Models

Adversarial skill embeddings for training reusable controllers for physically simulated characters.

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

Gated-Shape CNN for Semantic Segmentation (ICCV 2019)

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)

No description.

Latent Point Diffusion Models for 3D Shape Generation

Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)

No description.

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)

[ICCV 2025] PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

Physically-Plausible Image Signal Processing (PPISP) for Radiance Field Reconstruction

[CVPR'25 Oral] Official implementation for "DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models"

No description.

Code for "ATISS: Autoregressive Transformers for Indoor Scene Synthesis", NeurIPS 2021

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Official implementation for SIGGRAPH 2023 paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"

[NeurIPS 2024] L4GM: Large 4D Gaussian Reconstruction Model

Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

No description.

NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.

[CVPR'26] TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

Learning Deformable Tetrahedral Meshes for 3D Reconstruction (NeurIPS 2020)

Official repo for SemanticGAN https://nv-tlabs.github.io/semanticGAN/

Meta-Sim: Learning to Generate Synthetic Datasets (ICCV 2019)

Code for CVPR 2022 paper "Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior"

Implementation of "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation" from CVPR Workshop on Human Motion Generation 2024.

[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

Official implementation of TRACE, the TRAjectory Diffusion Model for Controllable PEdestrians, from the CVPR 2023 paper: "Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion".

[SIGGRAPH 2024] Diffusion Texture Painting

No description.

Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations

[NeurIPS 2025] UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

Official Repository for the NVIDIA Fixer model

Official implementation of PACER, Pedestrian Animation ControllER, of CVPR 2023 paper: "Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion".

No description.

Differentially Private Diffusion Models

Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

Code release for DriveGAN (CVPR 2021)

No description.

GENIE: Higher-Order Denoising Diffusion Solvers

No description.

project page: https://nv-tlabs.github.io/big-datasetgan/

Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human Interaction Motions in Scenes with Text Control".

No description.

VoMP: Predicting Volumetric Mechanical Property Fields

Learning to Evaluate Perception Models Using Planner-Centric Metrics

Cosmos-Transfer1-7B-Sample-AV Toolkits

No description.

No description.

Code accompanying Neural Brushstroke Engine paper, SIGGRAPH Asia 2022

[ICML 2026] Official code for paper: Test-Time Training with KV Binding Is Secretly Linear Attention

[NeurIPS 2025] LuxDiT: Lighting Estimation with Video Diffusion Transformer

Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation (ECCV 2020)

Project page for GameGAN

No description.

No description.

[SIGGRAPH 2025] Painting with 3D Gaussian Splat Brushes

No description.

No description.

No description.

Implementation of ReMatching Dynamic Reconstruction Flow (ICLR 2025) for augmenting dynamic scene reconstruction methods with designed velocity-field priors.

No description.

https://nv-tlabs.github.io/semanticGAN/

No description.

Federated Simulation for Medical Imaging (MICCAI2020)

No description.

No description.

No description.

No description.

NTG - Neural Turtle Graphics for Modeling City Road Layouts (ICCV 2019)

https://nv-tlabs.github.io/big-datasetgan/

Project page for "Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting" (ICCV 2021)

XDGAN: Multi-Modal 3D Shape Generation in 2D Space

No description.

No description.

Project page of Neural Fields as Learnable Kernels for 3D Reconstruction.

No description.

No description.

No description.

No description.

No description.

Stochastic Preconditiong for Neural Field Optimization -- additional website assets

No description.

No description.

No description.

Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation

Project page for the paper "How Much More Data Do I Need? Estimating Requirements For Downstream Tasks".

Assets of ReMatching Dynamic Reconstruction Flow (ICLR 2025)

The prior NVIDIA Toronto AI Lab public website, now renamed to the Spatial Intelligence Lab (SIL) and redirecting there.

No description.

No description.

No description.

Project page for DP-Sinkhorn (Neurips 2021)

Project page for the paper "Optimizing Data Collection In Machine Learning"

hugo backend for the main page

No description.

Project page for "Learning to Evaluate Perception Models using Planner-Centric Metrics"

No description.

No description.