Search Results for author:
Found 26 papers, 15 papers with code
Unsupervised Learning of Optical Flow with Deep Feature Similarity
Deep unsupervised learning for optical flow has been proposed, where the loss measures image similarity with the warping function parameterized by estimated flow.
SemCity: Semantic Scene Generation with Triplane Diffusion
In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset.
UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Sets
Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes.
Deep Video Inpainting Guided by Audio-Visual Self-Supervision
To implement the prior knowledge, we first train the audio-visual network, which learns the correspondence between auditory and visual information.
Towards Content-based Pixel Retrieval in Revisited Oxford and Paris
To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis.
Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising
Then we design our ensembling network to obtain per-pixel ensembling weight maps, which represent pixel-wise guidance for which auxiliary feature should be dominant at reconstructing each individual pixel and use them to ensemble the two denoised results of our denosiers.
Feature Separation and Recalibration for Adversarial Robustness
The Separation part disentangles the input feature map into the robust feature with activations that help the model make correct predictions and the non-robust feature with activations that are responsible for model mispredictions upon adversarial attack.
Take a Prior from Other Tasks for Severe Blur Removal
For general scene deblurring, the feature space of the blurry image and corresponding sharp image under the high-level vision task is closer, which inspires us to rely on other tasks (e. g. classification) to learn a comprehensive prior in severe blur removal cases.
Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data
To the best of our knowledge, our work is the first to apply discrete and latent diffusion for 3D categorical data on a scene-scale.
Contour-Aware Equipotential Learning for Semantic Segmentation
This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions.
Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality.
Semi-Supervised Learning of Optical Flow by Flow Supervisor
A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset.
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features.
Ranked #3 on
Unsupervised Vehicle Re-Identification
on VeRi-776
Hypergraph Propagation and Community Selection for Objects Retrieval
However, existing query expansion and diffusion methods cannot efficiently propagate the spatial information in an ordinary graph with scalar edge weights, resulting in low recall or precision.
Ranked #1 on
Image Retrieval
on RParis (Medium)
In-N-Out: Towards Good Initialization for Inpainting and Outpainting
Our self-supervision method, In-N-Out, is summarized as a training approach that leverages the knowledge of the opposite task into the target model.
A Method for Estimating Reflectance map and Material using Deep Learning with Synthetic Dataset
In this paper, we propose a deep learning-based reflectance map prediction system for material estimation of target objects in the image, so as to alleviate the ill-posed problem that occurs in this image decomposition operation.
Virtual Piano using Computer Vision
Especially for detecting intensity, a new method of utilizing spatial, temporal CNNs model is devised.
Real-time 3-D Mapping with Estimating Acoustic Materials
This paper proposes a real-time system integrating an acoustic material estimation from visual appearance and an on-the-fly mapping in the 3-dimension.
An Objectness Score for Accurate and Fast Detection during Navigation
We propose a novel method utilizing an objectness score for maintaining the locations and classes of objects detected from Mask R-CNN during mobile robot navigation.
Learning Embedding of 3D models with Quadric Loss
Sharp features such as edges and corners play an important role in the perception of 3D models.
Two-stream Spatiotemporal Feature for Video QA Task
Understanding the content of videos is one of the core techniques for developing various helpful applications in the real world, such as recognizing various human actions for surveillance systems or customer behavior analysis in an autonomous shop.
Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization
At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them.
Single Image Reflection Removal with Physically-Based Training Images
Recently, deep learning-based single image reflection separation methods have been exploited widely.
Light Field Neural Network
We introduce an optical neural network system made by off-the-shelf components.
Shortlist Selection With Residual-Aware Distance Estimator for K-Nearest Neighbor Search
We have tested the proposed method with the inverted index and multi-index on a diverse set of benchmarks including up to one billion data points with varying dimensions, and found that our method robustly improves the accuracy of shortlists (up to 127% relatively higher) over the state-of-the-art techniques with a comparable or even faster computational cost.
Distance Encoded Product Quantization
This result is achieved mainly because our method accurately estimates distances between two data points with the new binary codes and distance metric.
