[CVPR 2025] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

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

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Open reproduction of MUSE for fast text2image generation.

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

[3DV'25] 3D Reconstruction with Spatial Memory

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)

Grounding Image Matching in 3D with MASt3R

Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

[CVPR2024] Official implementation of SplattingAvatar.

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

Code of the paper: 6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model

my paper reading list

[ECCV 2024] SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model

Project Page for Paper "Deep Learning-Based Object Pose Estimation: A Comprehensive Survey"

ECCV 2024 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2024论文和开源项目

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Code repository for "ZeroShape: Regression-based Zero-shot Shape Reconstruction".

3D object reconstruction with multi-view RGB-D images.