Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences

Unified framework for robot learning built on NVIDIA Isaac Sim

Pytorch implementation of Self-Refining Video Sampling

Flux 2 image generation model pure C inference

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

[CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One

Official Implementation of Paper [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation]

Code Release of MVInverse: Feedforward Multi-view Inverse Rendering in Seconds

3D Reconstruction of Indoor Scenes with a Generative Framework

G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering.

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Sharp Monocular View Synthesis in Less Than a Second

[I3D 2024] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images

🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

[NeurIPS 2025] the official project page of a paper, "PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting"

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

LLM Council works together to answer your hardest questions

[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes

[ICLR 2026] Generative View Stitching

Depth Anything 3

[ICLR 2025] EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"

Official Implementation of "Towards Realistic Example-based Modeling via 3D Gaussian Stitching"

Official implementation of the paper "GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation"