Trending repositories for topic 3d-reconstruction
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 2days)
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
A procedural Blender pipeline for photorealistic training image generation
[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
[IROS 2023] Fast LiDAR-Inertial Odometry via Incremental Plane Pre-Fitting and Skeleton Tracking
3D object reconstruction with multi-view RGB-D images.
[IROS 2023] Fast LiDAR-Inertial Odometry via Incremental Plane Pre-Fitting and Skeleton Tracking
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 2days)
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (ECCV 2024)
[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
A procedural Blender pipeline for photorealistic training image generation
[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 2days)
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
A procedural Blender pipeline for photorealistic training image generation
[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.
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
[IROS 2023] Fast LiDAR-Inertial Odometry via Incremental Plane Pre-Fitting and Skeleton Tracking
Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
3D object reconstruction with multi-view RGB-D images.
SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data
RGBD-3DGS-SLAM is a monocular SLAM system leveraging 3D Gaussian Splatting (3DGS) for accurate point cloud and visual odometry estimation. By integrating neural networks, it estimates depth and camera...
[ICCV 2023] PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[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.
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 2days)
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Demonstration of different algorithms and operations on faces. Star the repo⭐
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
A procedural Blender pipeline for photorealistic training image generation
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
😎 GsplatLoc 🎯: Ultra-Precise Pose Optimization via 3D Gaussian Reprojection 🌟
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
RGBD-3DGS-SLAM is a monocular SLAM system leveraging 3D Gaussian Splatting (3DGS) for accurate point cloud and visual odometry estimation. By integrating neural networks, it estimates depth and camera...
[ICRA2025] Integrates the vision, touch, and common-sense information of foundational models, customized to the agent's perceptual needs.
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis
[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
StereoVision-SLAM is a real-time visual stereo SLAM (Simultaneous Localization and Mapping)
An open survey on 3D Gaussian Splatting compression methods
Code for "Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting" (ECCV 24 workshops)
Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
[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.
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[arXiv'24] [Image-to-Scene on a 4090(24G)] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering
[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.
A Modular Framework for 3D Gaussian Splatting and Beyond
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[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.
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
A Modular Framework for 3D Gaussian Splatting and Beyond
[arXiv'24] [Image-to-Scene on a 4090(24G)] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (ECCV 2024)
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
[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.
Official Code for 'TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction'
[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
[CVPR'24] MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video
[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D...