Point Clouds
18 papers with code • 2 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Point Clouds
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
DTU
Tanks and Temples
Most implemented papers
EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo
mindspore-ai/models
•
•
ICCV 2021
As a result, we achieve promising results on all datasets and the highest F-Score on the online TNT intermediate benchmark.
MVSNet: Depth Inference for Unstructured Multi-view Stereo
We present an end-to-end deep learning architecture for depth map inference from multi-view images.
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
alibaba/cascade-stereo
•
•
CVPR 2020
The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity.
Structure-From-Motion Revisited
Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections.
Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness
touristCheng/UCSNet
•
•
CVPR 2020
In contrast, we propose adaptive thin volumes (ATVs); in an ATV, the depth hypothesis of each plane is spatially varying, which adapts to the uncertainties of previous per-pixel depth predictions.
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
JiayuYANG/CVP-MVSNet
•
•
CVPR 2020
We propose a cost volume-based neural network for depth inference from multi-view images.
Visibility-aware Multi-view Stereo Network
As such, the adverse influence of occluded pixels is suppressed in the cost fusion.
PatchmatchNet: Learned Multi-View Patchmatch Stereo
FangjinhuaWang/PatchmatchNet
•
•
CVPR 2021
We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo.
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
qt-zhu/aa-rmvsnet
•
•
ICCV 2021
To overcome the difficulty of varying occlusion in complex scenes, we propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, which is able to preserve better-matched pairs among all views.
Generalized Binary Search Network for Highly-Efficient Multi-View Stereo
mizhenxing/gbi-net
•
•
CVPR 2022
The new formulation makes our method only sample a very small number of depth hypotheses in each step, which is highly memory efficient, and also greatly facilitates quick training convergence.
