Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[ICCV 2025] MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion

GPU accelerated utilities for data on HEALPix grids

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

Multi-view evaluation program.

[CVPR 2026] Visual Geometry Transformer for Autonomous Driving

DeepSphere: a graph-based spherical CNN (PyTorch)

Convolutions on the sphere with HEALPix pixelization

A flexible, high-performance 3D simulator for Embodied AI research.

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Tooling for the Common Objects In 3D dataset.

Display (binary) .npy or .npz files in VSCode.

Focused malicious code detection ruleset, with a high protection-to-noise ratio

Public release of the code for "Accelerating Vision Transformers with Adaptive Patches"

[CVPR2020] BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

This is PyTorch implementation of our paper "LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network".(CVPR'22)

Official implementation of HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

[CVPR 2024] No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

[ICLR'24] GTA: A Geometry-Aware Attention Mechanism for Multi-view Transformers

🍳 [CVPR'24 Highlight] Pytorch implementation of "Taming Stable Diffusion for Text to 360° Panorama Image Generation"

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

A conda-forge distribution.

[CVPR 2025] Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images