Trending repositories for topic 3d-reconstruction
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[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
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
[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.
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
A procedural Blender pipeline for photorealistic training image generation
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
Spatiotemporal modeling of spatial transcriptomics
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
[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
[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...
[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.
[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.
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
Monocular Structured-Light 3D Reconstruction，:star: if you like.
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
Spatiotemporal modeling of spatial transcriptomics
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[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
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
[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
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Spatiotemporal modeling of spatial transcriptomics
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
An open survey on 3D Gaussian Splatting compression methods
"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
[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...
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.
[NeurIPS 2024] VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
[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.
[3DV'24 Best Paper Honorable Mention] NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
Spatiotemporal modeling of spatial transcriptomics
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.
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
"Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction" (NeurIPS 2024)
[NeurIPS 2024] VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
Spatiotemporal modeling of spatial transcriptomics
Official Implementation of BMVC 2024 paper titled "HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images"
An open survey on 3D Gaussian Splatting compression methods
"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)
StereoVision-SLAM is a real-time visual stereo SLAM (Simultaneous Localization and Mapping)
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Official implementation of the paper " FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything "
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt.
Generate 3D meshes from 2D images and retexture them directly in Unity.
[IROS 2023] Fast LiDAR-Inertial Odometry via Incremental Plane Pre-Fitting and Skeleton Tracking
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]
[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.
[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
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
[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...
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..."
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]
[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.
[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
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.
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting
[CVPR 2024 Highlight] Official repository for paper "SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction"
"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (ECCV 2024)
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
[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...
EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis
[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.
[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