Search Results for author:
Found 10 papers, 4 papers with code
NARUTO: Neural Active Reconstruction from Uncertain Target Observations
We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction.
PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works.
Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules.
CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation
To this end, we propose CLIP-FLow, a semi-supervised iterative pseudo-labeling framework to transfer the pretraining knowledge to the target real domain.
RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo
At the pixel level, we propose to break the symmetry of the Siamese network (which is typically used in MVS to extract image features) by introducing a transformer block to the reference image (but not to the source images).
PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo
The semantic plane detection branch is based on a single-view plane detection framework but with differences.
Do End-to-end Stereo Algorithms Under-utilize Information?
In this paper, we show how deep adaptive filtering and differentiable semi-global aggregation can be integrated in existing 2D and 3D convolutional networks for end-to-end stereo matching, leading to improved accuracy.
Matching-space Stereo Networks for Cross-domain Generalization
End-to-end deep networks represent the state of the art for stereo matching.
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
The success of these methods is due to the availability of training data with ground truth; training learning-based systems on these datasets has allowed them to surpass the accuracy of conventional approaches based on heuristics and assumptions.
