3D Reconstruction

3D Reconstruction is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.

Image: Gwak et al

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 981–990 of 2326 papers

Title	Date	Tasks	Status
Improving the generalization of network based relative pose regression: dimension reduction as a regularizer	Oct 24, 2020	3D ReconstructionDimensionality Reduction	—Unverified
Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models	Jun 12, 2024	3D Reconstruction	—Unverified
Enhanced fringe-to-phase framework using deep learning	Feb 1, 2024	3D ReconstructionDeep Learning	—Unverified
Enforcing 3D Topological Constraints in Composite Objects via Implicit Functions	Jul 16, 2023	3D Object Reconstruction3D Reconstruction	—Unverified
BS3D: Building-scale 3D Reconstruction from RGB-D Images	Jan 3, 2023	3D ReconstructionDepth Estimation	—Unverified
AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards	May 20, 2025	3D Reconstruction	—Unverified
DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction	Dec 1, 2019	3D Reconstruction	—Unverified
EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion	Oct 5, 2024	3D ReconstructionDepth Estimation	—Unverified
Energy Based Multi-model Fitting & Matching for 3D Reconstruction	Jun 1, 2014	3D Reconstructionvalid	—Unverified
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images	Jul 16, 2025	3D ReconstructionCamera Pose Estimation	—Unverified

Show:10 25 50

← PrevPage 99 of 233Next →

All datasets DTU ShapeNet Data3D−R2N2 Scan2CAD 3DPeople Aria Digital Twin Dataset Aria Synthetic Environments ScanNet

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	3D-R2N2	Overall	0.63	—	Unverified
2	Gipuma	Overall	0.58	—	Unverified
3	COLMAP	Overall	0.53	—	Unverified
4	MVSNet	Overall	0.46	—	Unverified
5	Vis-MVSNet	Overall	0.37	—	Unverified
6	AA-RMVSNet	Overall	0.36	—	Unverified
7	Cas-MVSNet	Overall	0.36	—	Unverified
8	EPP-MVSNet	Overall	0.36	—	Unverified
9	PatchmatchNet	Overall	0.35	—	Unverified
10	CVP-MVSNet	Overall	0.35	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MD-GON	IoU	92.8	—	Unverified
2	POCO	IoU	92.6	—	Unverified
3	FS-SDF	IoU	91.2	—	Unverified
4	DP-ConvONet	IoU	89.5	—	Unverified
5	ConvONet	IoU	88.4	—	Unverified
6	ONet	IoU	76.1	—	Unverified
7	EVolT	IoU	73.8	—	Unverified
8	ZubicLio	IoU	65.43	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AttSets	3DIoU	0.64	—	Unverified
2	PSGN	3DIoU	0.64	—	Unverified
3	OGN	3DIoU	0.6	—	Unverified
4	3D-R2N2	3DIoU	0.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Scan2CAD	Average Accuracy	31.68	—	Unverified
2	3DMatch	Average Accuracy	10.29	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SVCP	Chamfer	10	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EVL	Accuracy	18.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EVL	Accuracy	5.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Atlas (finetuned)	3DIoU	89.4	—	Unverified