Search Results for author:
Found 6 papers, 4 papers with code
KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo
Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth.
Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives
Recently, Implicit Neural Representations (INRs) parameterized by neural networks have emerged as a powerful and promising tool to represent different kinds of signals due to its continuous, differentiable properties, showing superiorities to classical discretized representations.
TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images.
Ranked #4 on
3D Reconstruction
on DTU
MegLoc: A Robust and Accurate Visual Localization Pipeline
In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years.
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
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.
Ranked #5 on
Point Clouds
on Tanks and Temples
(Mean F1 (Intermediate) metric)
Deep Learning for Multi-View Stereo via Plane Sweep: A Survey
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality.
