Search Results for author:
Found 50 papers, 21 papers with code
Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information
Geometry problem solving has garnered increasing attention due to its potential applications in intelligent education field.
GNN-Coder: Boosting Semantic Code Retrieval with Combined GNNs and Transformer
Code retrieval is a crucial component in modern software development, particularly in large-scale projects.
Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning
In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples.
MagicGeo: Training-Free Text-Guided Geometric Diagram Generation
Geometric diagrams are critical in conveying mathematical and scientific concepts, yet traditional diagram generation methods are often manual and resource-intensive.
A Survey on LLM-powered Agents for Recommender Systems
Recommender systems are essential components of many online platforms, yet traditional approaches still struggle with understanding complex user preferences and providing explainable recommendations.
Process-Supervised Reinforcement Learning for Code Generation
Notably, in tackling complex code generation tasks, process-supervised reinforcement learning shows a clear advantage, ensuring both the integrity of the code generation process and the correctness of the generation results.
Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors
Building on this, a large-scale portrait matting dataset is created, termed LD-Portrait-20K, with $20, 051$ portrait foregrounds and high-quality alpha mattes.
Rethinking Model Redundancy for Low-light Image Enhancement
Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance: Attention Dynamic Reallocation (ADR) and Parameter Orthogonal Generation (POG).
Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising
RDC renoises the predicted denoised image by the predicted noise to construct multiple noisy images, preserving all the information of the original image.
Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
The prior reveals the complementary correlation of NIR and RGB images in the frequency domain.
ULMRec: User-centric Large Language Model for Sequential Recommendation
To alleviate this problem, in this paper, we propose ULMRec, a framework that effectively integrates user personalized preferences into LLMs for sequential recommendation.
ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
In this paper, we investigate the task of general conversational image retrieval on open-domain images.
Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks.
EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching
Specifically, our method utilizes a Temporal Recurrent Network to aggregate event features across temporal or spatial domains, and a Spatial Contextual Attention to enhance knowledge transfer across event flows via temporal or spatial interactions.
Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
However, current methods often prioritize the extraction of temporal information from continuous event flow, leading to an overemphasis on low-frequency texture features in the scene, resulting in over-smoothing and blurry artifacts.
Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer
To this end, we introduce a Locally Noise Prior Estimation (LoNPE) algorithm, which accurately estimates the noise prior directly from a single raw noisy image.
Exploiting Frequency Correlation for Hyperspectral Image Reconstruction
Leveraging the HFC prior, we subsequently establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF) targeting low-frequency and high-frequency components, respectively.
4-bit Shampoo for Memory-Efficient Network Training
In this paper, we propose the first 4-bit second-order optimizers, exemplified by 4-bit Shampoo, maintaining performance similar to that of 32-bit ones.
MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models
However, the method of generating illumination maps has poor generalization performance and parametric models such as Spherical Harmonic (SH) and Spherical Gaussian (SG) fall short in capturing high-frequency or low-frequency components.
SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream
Spike cameras, leveraging spike-based integration sampling and high temporal resolution, offer distinct advantages over standard cameras.
Finding Visual Saliency in Continuous Spike Stream
Our framework exhibits a substantial margin of improvement in capturing and highlighting visual saliency in the spike stream, which not only provides a new perspective for spike-based saliency segmentation but also shows a new paradigm for full SNN-based transformer models.
Physics-Inspired Degradation Models for Hyperspectral Image Fusion
To fill this gap, we propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI, which comprises a spatial degradation network (SpaDN) and a spectral degradation network (SpeDN).
CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning
However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge.
Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency
Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications.
In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging
Dual-Camera Compressed Hyperspectral Imaging (DCCHI) offers the capability to reconstruct 3D Hyperspectral Image (HSI) by fusing compressive and Panchromatic (PAN) image, which has shown great potential for snapshot hyperspectral imaging in practice.
Physics-guided Noise Neural Proxy for Practical Low-light Raw Image Denoising
Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-guided proxy model (PPM), and differentiable distribution loss (DDL).
Recurrent Spike-based Image Restoration under General Illumination
Spike camera is a new type of bio-inspired vision sensor that records light intensity in the form of a spike array with high temporal resolution (20, 000 Hz).
SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views
The recent neural surface reconstruction by volume rendering approaches have made much progress by achieving impressive surface reconstruction quality, but are still limited to dense and highly accurate posed views.
Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding.
Ranked #1 on
Color Image Denoising
on ImageNet sigma250
SIND: A Drone Dataset at Signalized Intersection in China
Then, the behaviors of traffic light violations in SIND are recorded.
Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream.
Ranked #1 on
Image Denoising
on SID SonyA7S2 x100
Revisiting Competitive Coding Approach for Palmprint Recognition: A Linear Discriminant Analysis Perspective
Based on our analysis, we examined the statistics of palmprints and concluded that CompCode deviates from the optimal condition.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Quantization-Aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging
In this paper, we propose the quantization-aware deep optics for diffractive snapshot hyperspectral imaging.
Image-specific Convolutional Kernel Modulation for Single Image Super-resolution
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.
Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework
Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.
Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning
Unlike existing FL methods, our IGFL can be applied to both client and server optimization.
Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction
Snapshot hyperspectral imaging has been developed to capture the spectral information of dynamic scenes.
Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.
Snapshot Hyperspectral Imaging Based on Weighted High-order Singular Value Regularization
In this paper, we propose an effective high-order tensor optimization based method to boost the reconstruction fidelity for snapshot hyperspectral imaging.
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
In this work, we present a class of tuning-free PnP proximal algorithms that can determine parameters such as denoising strength, termination time, and other optimization-specific parameters automatically.
Acoustic Echo Cancellation by Combining Adaptive Digital Filter and Recurrent Neural Network
In this paper, a fusion scheme by combining adaptive filter and neural network is proposed for AEC.
A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising
Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training.
Ranked #5 on
Image Denoising
on ELD SonyA7S2 x200
3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along spectrum.
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Moreover, we discuss the practical considerations of the plugged denoisers, which together with our learned policy yield state-of-the-art results.
Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selection
Then we use multi-task optimization to train the normal estimation and local plane classification tasks simultaneously. Also, to integrate the advantages of multi-scale results, a scale selection strategy is adopted, which is a data-driven approach for selecting the optimal scale around each point and encourages subnetwork specialization.
Playing Atari Ball Games with Hierarchical Reinforcement Learning
We argue that these instructions have tremendous value in designing a reinforcement learning system which can learn in human fashion, and we test the idea by playing the Atari games Tennis and Pong.
Accelerated Variance Reduced Stochastic Extragradient Method for Sparse Machine Learning Problems
Moreover, our theoretical analysis shows that AVR-SExtraGD enjoys the best-known convergence rates and oracle complexities of stochastic first-order algorithms such as Katyusha for both strongly convex and non-strongly convex problems.
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements
Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems.
Ranked #3 on
Reflection Removal
on SIR^2(Objects)
Image Restoration from Patch-based Compressed Sensing Measurement
A series of methods have been proposed to reconstruct an image from compressively sensed random measurement, but most of them have high time complexity and are inappropriate for patch-based compressed sensing capture, because of their serious blocky artifacts in the restoration results.
