Official implementation of the ICML 2025 paper "Learning Survival Distributions with the Asymmetric Laplace Distribution".

Official inference repo for FLUX.1 models

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

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

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

Official implementation of Continuous 3D Perception Model with Persistent State

Official implementation of "DepthLab: From Partial to Complete"

🤗 image matching webui

[CVPR 2025] Relative camera pose estimation and visual localization with Reloc3r

[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

News: the 10k dataset is ready for download.

[SCIA 2025] NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation

Tracking Any Point (TAP)

GLOMAP - Global Structured-from-Motion Revisited

[ECCV'24] Differentiable Product Quantization for Memory Efficient Camera Relocalization

3D reconstruction + 3D open vocablurary semantic segmentation all in onece

Grounding Image Matching in 3D with MASt3R

Code release for CVPR'24 submission 'OmniGlue'

DUSt3R + Gaussian Splatting

Minimal solvers for calibrated camera pose estimation

[3DV 2025] Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024

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

DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Grok open release

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