Let us control diffusion models!

[CVPR'22] CrossLoc localization: a cross-modal visual representation learning method for absolute localization

Grounding Image Matching in 3D with MASt3R

Cross-Domain UAV Pose Estimation: A Novel Attempt in UAV Visual Localization

[ICCV 2025] ACE-G is an architecture and pre-training scheme to improve generalization for scene coordinate regression-based visual relocalization.

DUSt3R: Geometric 3D Vision Made Easy

MCP for xiaohongshu.com

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

[IROS 2024] Leveraging Neural Radiance Field in data synthesis for D2S

CVPR 2025 论文和开源项目合集

Disk code release

[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching

Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".

Official repository for paper "Scene-agnostic Pose Regression for Visual Localization" (SPR), CVPR 2025

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

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

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[CVPR'22] TOPO-DataGen: an open and scalable aerial synthetic data generation workflow

Code release for NeRF (Neural Radiance Fields)

Dense Prediction Transformers

[ICRA 2025 & RAL 2024] D2S: Representing sparse descriptors and 3D coordinates for camera relocalization

Instant neural graphics primitives: lightning fast NeRF and more

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

RA-L 2025

Official repository for R2Former: Unified Retrieval and Reranking Transformer for Place Recognition