Search Results for author:
Found 12 papers, 6 papers with code
CoMatcher: Multi-View Collaborative Feature Matching
This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios.
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
We achieve this by ensuring the poisoned model's loss function has a similar value as a normally trained model at each input sample but with a large local curvature.
PolyRoom: Room-aware Transformer for Floorplan Reconstruction
To tackle these challenges, we present PolyRoom, a room-aware Transformer that leverages uniform sampling representation, room-aware query initialization, and room-aware self-attention for floorplan reconstruction.
Stratified Avatar Generation from Sparse Observations
This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the head and hands.
PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images
Instead of solving the problem in the motion averaging phase we focus on estimating scaled relative pose with the help of panoramic cameras and deep neural networks.
Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo
This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation for accurate PatchMatch Multi-View Stereo (MVS).
Shape Anchor Guided Holistic Indoor Scene Understanding
This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding.
Holistic Geometric Feature Learning for Structured Reconstruction
The inference of topological principles is a key problem in structured reconstruction.
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.
A multi-domain splitting framework for time-varying graph structure
To address the anomaly detection problem for datasets with a spatial-temporal structure, in this work, we propose a novel graph multi-domain splitting framework, called GMDS, by integrating the time, vertex, and frequency features to locate the anomalies.
Unmixing Convolutional Features for Crisp Edge Detection
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.
Ranked #2 on
Edge Detection
on MDBD
ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
In this paper, a practical and efficient edge-aware neural network is presented for semantic segmentation.
