Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks121 from public data
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey651
This paper proposes a low-light image and video dataset, in which the images and videos are taken by different mobile phones’ cameras under diverse illumination conditions, and provides a unified online platform that covers many popular LLIE methods.
- Geometry-Aware Learning of Maps for Camera Localization456
This work proposes to represent maps as a deep neural net called MapNet, which enables learning a data-driven map representation and proposes a novel parameterization for camera rotation which is better suited for deep-learning based camera pose regression.
- MapNet: Geometry-Aware Learning of Maps for Camera Localization456
This work proposes to represent maps as a deep neural net called MapNet, which enables learning a data-driven map representation and proposes a novel parameterization for camera rotation which is better suited for deep-learning based camera pose regression.
- 320
- GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution305
This work shows that pre-trained Generative Adversarial Networks (GANs), e.g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR) and shows clear improvements in terms of fidelity and texture faithfulness in comparison to existing methods.
- 265
- PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image263
A deep neural architecture that detects and reconstructs piecewise planar regions from a single RGB image using a variant of Mask R-CNN and refines an arbitrary number of segmentation masks with a novel loss enforcing the consistency with a nearby view during training.
- World Simulation with Video Foundation Models for Physical AI211
This work introduces [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI, which unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation.
- Neural Inverse Rendering of an Indoor Scene From a Single Image183
This work proposes the first learning based approach that jointly estimates albedo, normals, and lighting of an indoor scene from a single image, and uses physically-based rendering to create a large-scale synthetic dataset, named SUNCG-PBR, which is a significant improvement over prior datasets.
- 182
- 164
- Neural RGB®D Sensing: Depth and Uncertainty From a Video Camera156
This paper proposes a deep learning method to estimate per-pixel depth and its uncertainty continuously from a monocular video stream, with the goal of effectively turning an RGB camera into an RGB-D camera.
- 145
- 142
- 135
- 132
- 128
- 125
- Time-varying surface appearance122
This paper describes the acquisition of the first time-varying database of 26 samples, encompassing a variety of natural processes including burning, drying, decay, and corrosion and derives an overall temporal appearance variation characteristic curve of the specific process, as well as space-dependent textures, rates, and offsets.
- 107
- Printing spatially-varying reflectance104
This work proposes a complete system that uses appropriate inks and foils to print documents with a variety of material properties, and automatically finds the optimal linear combinations to approximate the BRDFs of the target documents.
- 101
- A combination model for orientation field of fingerprints100
A polynomial model is used to approximate the orientation field globally and a point-charge model at each singular point to improve the approximation locally and this combination model is more accurate and robust with respect to noise compared with the previous works.
- Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment99
This work proposes a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS), and the resultant samples are named fragments, a network architecture tailored specifically for fragments that achieves up to 1612× efficiency than the existing state-of-the-art VQA benchmarks.
- 99
- Reblur2Deblur: Deblurring videos via self-supervised learning93
This work fine-tunes existing deblurring neural networks in a self-supervised fashion by enforcing that the output, when blurred based on the optical flow between subsequent frames, matches the input blurry image.
- 92
- Removing image artifacts due to dirty camera lenses and thin occluders92
This paper shows that dirt on camera lenses, and occlusions from thin objects such as fences, can be described by a single image formation model, wherein an intermediate layer both attenuates the incoming light and scatters stray light towards the camera.
- AIM 2020 Challenge on Learned Image Signal Processing Pipeline90
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results, defining the state-of-the-art for practical image signal processing pipeline modeling.
- Modeling orientation fields of fingerprints with rational complex functions83
A novel model is proposed for the orientation field of fingerprints, which can be expressed as the argument of a rational complex function, suitable for all types of fingerprints.
- Deep Fourier Up-Sampling80
The relationships between spatial and Fourier domains are revisited and the transform rules on the features of different resolutions in the Fourier domain are revealed, which provide key insights for FourierUp's designs.
- Separating Reflection and Transmission Images in the Wild76
This work presents a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance of semi-reflectors, and extensively validate this method against a number of related works on a new dataset of images captured in the wild.
- 69
- Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network65
A physics-based image formation model is defined to better understand the degradation of Under-Display Camera images, and a new domain knowledge-enabled Dynamic Skip Connection Network (DISCNet) is designed to restore the UDC images.
- 65
- 64
- ReconfigISP: Reconfigurable Camera Image Processing Pipeline56
This study proposes a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks, and enables back-propagation for each module by training a differentiable proxy, allowing to leverage the popular differentiable neural architecture search and effectively search for the optimal ISP architecture.
- A Lightweight Approach for On-the-Fly Reflectance Estimation51
This paper proposes a lightweight approach for surface reflectance estimation directly from 8-bit RGB images in real-time, which can be easily plugged into any 3D scanning-and-fusion system with a commodity RGBD sensor, and outperforms prior work forreflectance estimation in uncontrolled environments.
- 49
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions43
HDRFlow is the first real-time HDR video reconstruction method for video sequences captured with alternating exposures, capable of processing 720p resolution inputs at 25ms, and outperforms previous methods on standard benchmarks.
- iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging40
The transient representation is revisited, it can be integrated with different rule-based depth sensing algorithms that are robust to low SNR and can deal with ambiguous scenarios that arise in practice (e.g., specular MPI, optical cross-talk).
- Switchable Temporal Propagation Network40
This paper proposes a learnable unified framework for propagating a variety of visual properties of video images, including but not limited to color, high dynamic range (HDR), and segmentation information, where the properties are available for only a few key-frames.
- PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging38
A novel two-stage approach for consistent and photorealistic lensless image reconstruction that achieves a superior balance between data fidelity and visual quality compared to existing methods, as demonstrated with two popular lensless systems, PhlatCam and DiffuserCam.
- 38
- GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond36
The method, Generative LatEnt bANk (GLEAN), goes beyond existing practices by directly leveraging rich and diverse priors encapsulated in a pre-trained GAN, and extends to different tasks including image colorization and blind image restoration.
- ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary33
ArtiScene is a training-free automated pipeline for scene design that integrates the flexibility of free-form text-to-image generation with the diversity and reliability of 2D intermediary layouts, and outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics.
- Toward a Perceptually Based Metric for BRDF Modeling33
The results of this study show that the cube root metric leads to a better perceptual approximation than other RMS based metrics, independently of the analytical BRDF model used.
- Singular Points Analysis in Fingerprints Based on Topological Structure and Orientation Field33
It is proved that every completely captured fingerprint should have the same number of cores and deltas, and a novel algorithm for singular point detection using global orientation field is proposed.
- 32
- Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera30
This work revisits the classic stereo setup for training data collection and mitigate the non-trivial domain discrepancy and spatial misalignment through a novel Transformer-based framework that generates well-aligned yet high-quality target data for the corresponding UDC input.
- Real-Time Controllable Denoising for Image and Video29
Real-time Controllable Denoising (RCD) is introduced, the first deep image and video denoising pipeline that provides a fully controllable user interface to edit arbitraryDenoising levels in real-time with only one-time network inference.
- Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration28
AdaCode is a more flexible and expressive discrete generative prior than previous work and achieves state-of-the-art performance on image reconstruction and restoration tasks, including image super-resolution and inpainting.
- PolarFree: Polarization-based Reflection-Free Imaging27
A large-scale dataset, PolaRGB, is constructed for Polarization-based reflection removal of RGB images, which enables us to train models that generalize effectively across a wide range of real-world scenarios and introduces PolarFree, which leverages diffusion process to generate reflection-free cues for accurate reflection removal.
- 26
- 26
- Very Power Efficient Neural Time-of-Flight25
It is shown that despite the weak signals in many areas under extreme short exposure setting, these signals as a whole can be well utilized through a learning process which directly translates the weak and noisy ToF camera raw to depth map.
- 24
- 19
- Hidden annotation for image retrieval with long-term relevance feedback learning19
The work proposes to incorporate long-term relevance feedback (LRF) with HA to increase both efficiency and retrieval accuracy of CBIR systems.
- Matting by Generation18
An innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge and harnesses the capabilities of latent diffusion models, enriched with extensive pre-trained knowledge, to regularize the matting process.
- MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results18
The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal and a detailed description of all models developed is provided in this paper.
- 16
- NRMVS: Non-Rigid Multi-View Stereo16
It is shown that a dense reconstruction of a scene with non-rigid changes from a few images is possible, and it is demonstrated that the method can be used to interpolate novel deformed scenes from various combinations of deformation estimates derived from the sparse views.
- 14
- 14
- 12
- JPD-SE: High-Level Semantics for Joint Perception-Distortion Enhancement in Image Compression12
A three-phase training scheme that teaches semantic-aware codecs to leverage the power of semantic to jointly optimize rate-perception-distortion (R-PD) performance and boost the performance of downstream computer vision algorithms.
- Cosmos World Foundation Models for Physical AI11
An overview of Cosmos models, its development journey, benchmarking and evaluation, and various types of post-training of Cosmos models specifically targeting applications to robotics and autonomous driving are given.
- From Sim-to-Real: Toward General Event-based Low-light Frame Interpolation with Per-scene Optimization11
This work proposes a novel per-scene optimization strategy that utilizes the internal statistics of a sequence to handle degraded event data under low-light conditions, improving the generalizability to different lighting and camera settings.
- 11
- 11
- Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge10
This report presents the solution to the 2025 BEHAVIOR Challenge in a very close 2nd place and substantially outperforms the rest of the submissions, and reveals the scaling benefits in both the pre-training and post-training phases, leading to a validation Q-score of 0.345, significantly surpassing previous state-of-the-art performance.
- Learning-based lens wavefront aberration recovery10
A lightweight and practical learning-based method to recover the wavefront aberration for an imaging system from a single intensity measurement, named LWNet, which works well for wavefront aberration estimation of real imaging systems and consistently outperforms prior learning-based methods.
- 10
- Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising9
This work proposes a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG), which leverages a reconstructive denoising network to recover the majority of the underlying clean signal and employs a diffusion algorithm to generate residual high-frequency details, thereby enhancing visual quality.
- 9
- Deep camera obscura: an image restoration pipeline for pinhole photography9
An image restoration pipeline of thePinhole system is developed to enhance the pinhole image quality through joint denoising and deblurring and demonstrates high 2D image quality on real pinhole images that is on-par or slightly improved compared to other lensless cameras.
- A Physics-Informed Blur Learning Framework for Imaging Systems8
This paper introduces a novel wavefront-based PSF model accompanied by an optimization strategy, both reducing optimization complexity and improving estimation accuracy, and demonstrates improvements in image quality in simulation and also showcases noticeable visual quality improvements on real captured images.
- MIPI 2023 Challenge on RGBW Remosaic: Methods and Results8
This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023, and describes the top three models developed in this challenge.
- 7
- Cached Transformers: Improving Transformers with Differentiable Memory Cache7
This work introduces a new Transformer model that uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens, and surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.
- 7
- 7
- MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Results6
The results of the competition are presented, the strengths and weaknesses of the top-performing methods are analyzed, and the implications of the findings for future research in RGB+sparse ToF depth completion are discussed.
- 6
- Parallel Sequence Modeling via Generalized Spatial Propagation Network5
With learnable, input-dependent weights and no reliance on positional embeddings, GSPN achieves superior spatial fidelity and state-of-the-art performance in vision tasks, including ImageNet classification, class-guided image generation, and text-to-image generation.
- 5
- 4
- 4
- 4
- 3
- 3
- MIPI 2023 Challenge on RGBW Fusion: Methods and Results3
This paper summarizes and reviews the RGBW Joint Fusion and Denoise track on MIPI 2023 and describes the models developed in this challenge, including PSNR, SSIM, LPIPS, and KLD.
- JPAD-SE: High-Level Semantics for Joint Perception-Accuracy-Distortion Enhancement in Image Compression.3
This paper presents a generic framework that can enable any image codec to leverage high-level semantics, and argues that semantic enhancement implicitly optimizes rate-perception-accuracy-distortion (R-PAD) performance.
- 3
- 3
- Rapid and Brief Communication Modeling orientation %elds of %ngerprints with rational complex functions3
A novel model is proposed for the orientation of %eld of %ngerprints, which can be expressed as the argument of a rational complex function, suitable for all types of patterns.
- An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification2
This paper proposes a face center alignment scheme, an augmentation curriculum to build robustness against variations, and a knowledge distillation method to smooth optimization and enhance performance that outperforms two-stage lensless verification while enhancing privacy and efficiency.
- LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification2
This paper proposes a face center alignment scheme, an augmentation curriculum to build robustness against variations, and a knowledge distillation method to smooth optimization and enhance performance for privacy-preserving face verification directly on encoded lensless captures.
- Graphical Representation of Fingerprint Images2
This chapter introduces minutiae-based representation of fingerprints, provides some models for the graphical representation of orientation fields, and deals with the generation of synthetic fingerprint images.
- 2
- 2
- Uni-ISP: Towards Unifying the Learning of ISPs from Multiple Mobile Cameras1
Uni-ISP is introduced, a novel pipeline that unifies ISP learning for diverse mobile cameras, delivering a highly accurate and adaptable processor and unlocking new applications previously inaccessible to conventional learned ISPs.
- 1
- Random Weights Networks Work as Loss Prior Constraint for Image Restoration1
The main focus is to spark the realms of loss function and save their current neglected status and present the belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''.
- Research on different classifiers of automatic target recognition and classification for low-resolution ground radar1
A new neural network structure named multi-scale residual neural network (Multi-scale ResNet) is proposed for one-dimensional feature target recognition, which effectively reduces the data dimension through auto-encoder and solves the problem of performance degradation caused by the difficulty in training too many levels of traditional convolutional neural network.
- 1
- 1
- Measurement, modeling, and synthesis of time-varying appearance of natural phenomena1
A physically-based analytic reflectance model for recreating the weathered appearance of transparent surfaces in real time is derived, and single-image based methods to measure contaminant texture patterns from real samples are developed.
- MotionDreamer: Generating Continuous Intermediate Motions for Complex Motion Interpolation–
MotionDreamer is a novel framework that instills effective motion priors for all intermediate frames to video generators by regularizing diffusion training with ground truth continuous intermediate motions and collects the first open-source large-scale dataset, VFIVid, for complex motion interpolation.
- –
- –
- –
- –
- –
- Advances of Computational Imaging on Mobile Phones–
This talk will present several latest research results including high quality image restoration and accurate depth estimation from time-of-flight sensors or monocular videos, as well as some latest computational photography products in smart phones including under-display cameras, AI image sensors and AI ISP chips.
- –
- –
- –
- –
- Biometrics Project: Bayesian Face Recognition–
A 2D face recognition algorithm proposed in [2], which models the density of intrapersonal and extrapersonal face space separately with a single Gaussian for each, and thus uses Bayesian theory to do classification.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.