Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Alan Conrad BovikSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works148 from public data
- 925
- MAXIM: Multi-Axis MLP for Image Processing755
The proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, de raining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models.
- 556
- CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers453
The extensive experiments on the V2V perception dataset, OPV2V, demonstrate that CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation and is shown to be generalizable to other tasks, including 1) BEV segmentation with single-agent multi-camera and 2) 3D object detection with multi-agent LiDAR systems.
- V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception344
V2V4Real introduces three perception tasks, including cooperative 3D object detection, cooperative3D object tracking, and Sim2Real domain adaptation for cooperative perception, and provides comprehensive benchmarks of recent cooperative perception algorithms on three tasks.
- RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content236
RAPIQUE combines and leverages the advantages of both quality-aware scene statistics features and semantics-aware deep convolutional features, allowing it to design the first general and efficient spatial and temporal (space-time) bandpass statistics model for video quality modeling.
- OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving136
OpenEMMA, an open-source end-to-end framework based on MLLMs that achieves significant improvements compared to the baseline when leveraging a diverse range of MLLMs by incor-porating the Chain-of- Thought reasoning process, achieves significant improvements compared to the baseline.
- Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving100
LightDiff is introduced, a domain-tailored framework designed to enhance the low-light image quality for autonomous driving applications that employs a multi-condition controlled diffusion model and employs perception-specific scores as rewards to guide the diffusion training process through reinforcement learning.
- MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers70
A multi-weather Transformer that aims to solve multiple weather-induced degradations using a single, unified architecture, and allows for a novel way of tuning, during application, to either a single type of weather restoration or to hybrid weather restoration without any retraining, offering greater controllability than existing methods.
- A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment70
A large-scale comparative evaluation is conducted to assess the capabilities and limitations of multiple temporal pooling strategies on blind VQA of usergenerated videos and proposes an ensemble pooling model built on top of high-performing temporal Pooling models.
- On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective60
A holistic framework for advancing trustworthiness in GenAI is established, paving the way for safer and more responsible integration of GenFMs into critical applications and releasing the toolkit for dynamic evaluation.
- 58
- 53
- BBAND INDEX: A NO-REFERENCE BANDING ARTIFACT PREDICTOR49
A new distortion-specific no-reference video quality model for predicting banding artifacts, called the Blind BANding Detector (BBAND index), which is inspired by human visual models.
- AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving46
This paper evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models, and found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness.
- SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models42
SleeperMark is a novel framework designed to embed resilient watermarks into T2I diffusion models, showing robustness against downstream fine-tuning and various attacks at both the image and model levels, with minimal impact on the model’s generative capability.
- Video Quality Assessment: A Comprehensive Survey40
A comprehensive survey of recent progress in the development of VQA algorithms and the benchmarking studies and databases that make them possible is presented and open research directions on study design and VQA algorithm architectures are analyzed.
- The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report39
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques.
- CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation38
This work in-troduce a novel method, dubbed CoDi, that adapts a pre-trained latent diffusion model to accept additional image conditioning inputs while significantly reducing the sampling steps required to achieve high-quality results.
- SPIRE: Semantic Prompt-Driven Image Restoration35
SPIRE is the first framework that supports fine-level instruction through language-based quantitative specification of the restoration strength, without the need for explicit task-specific design, and introduces a novel fusion mechanism that augments the existing ControlNet architecture by learning to rescale the generative prior, thereby achieving better restoration fidelity.
- Adaptive Debanding Filter31
The proposed debanding filter is able to adaptively smooth banded regions while preserving image edges and details, yielding perceptually enhanced gradient rendering with limited bit-depths.
- V2X-DGW: Domain Generalization for Multi-Agent Perception Under Adverse Weather Conditions29
A Domain Generalization based approach for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions, named V2X-DGW, to promote the performance in the unseen adverse weather conditions by learning only on the clean weather data.
- Bigger is not Always Better: Scaling Properties of Latent Diffusion Models29
An in-depth investigation into how model size influences sampling efficiency across varying sampling steps unveil a surprising trend: when operating under a given inference budget, smaller models frequently outperform their larger equivalents in generating high-quality results.
- 28
- Ntire 2025 Challenge on Short-Form Ugc Video Quality Assessment and Enhancement: Methods and Results26
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement, and introduces a new short-form UGC dataset tailored for single-image super-resolution, i.e., the KwaiSR dataset.
- FAVER: Blind quality prediction of variable frame rate videos26
A first-of-a-kind blind VQA model for evaluating HFR videos, which is dubbed the Framerate-Aware Video Evaluator w/o Reference (FAVER), which uses extended models of spatial natural scene statistics that encompass space-time wavelet-decomposed video signals, to conduct efficient frame rate sensitive quality prediction.
- Pik-Fix: Restoring and Colorizing Old Photos25
A novel reference-based end-to-end learning framework that is able to both repair and colorize old, degraded pictures and significantly outperforms previous state-of-the-art models using both qualitative comparisons and quantitative measurements is presented.
- A Survey on LLM-based Conversational User Simulation24
A novel taxonomy covering user granularity and simulation objectives is introduced and systematically analyzed core techniques and evaluation methodologies to keep the research community informed of the latest advancements in conversational user simulation.
- NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results24
An overview of the NTIRE 2025 Challenge on UGC Video Enhancement is presented, which constructed a set of 150 user-generated content videos without reference ground truth, which suffer from real-world degradations such as noise, blur, faded colors, compression artifacts, etc.
- 22
- Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling21
Agent Banana is proposed, a hierarchical agentic planner-executor framework for high-fidelity, object-aware, deliberative editing and its integration into real workflows that advances reliable, professional-grade agentic image editing and its integration into real workflows.
- Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs15
VQA benchmarks show that VISTA-R1-8B outperforms state-of-the-art baselines with similar sizes by 9.51%-18.72%, demonstrating VISTA-Gym as an effective training ground to unlock the tool-integrated reasoning capabilities for VLMs.
- Regression or classification? New methods to evaluate no-reference picture and video quality models15
A comprehensive benchmark experiment of popular no-reference quality models on recent in-the-wild picture and video quality datasets is conducted, providing reliable baselines for both evaluation methods to support further studies.
- 14
- 14
- 13
- AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results13
This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC), to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos.
- DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection12
Dynamic Prototype Updating (DPU) is proposed, a novel plug-and-play framework for multimodal OOD detection that accounts for intra-class variations that significantly improves OOD detection performances, setting a new state-of-the-art in multimodal OOD detection.
- 10
- 9
- Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing8
- 8
- A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality7
A comprehensive novel taxonomy of existing methods and comparative tables that categorize papers by their architectural designs and performance characteristics are presented, to identify key architectural components and training strategies that consistently yield these qualities.
- 7
- 7
- 7
- 7
- InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions6
A background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships is introduced, and a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames is proposed.
- 6
- 5
- 5
- 5
- Demystifying the Visual Quality Paradox in Multimodal Large Language Models5
A visual-quality paradox is uncovered: model, task, and even individual-instance performance can improve when images deviate from human-perceived fidelity, and the need for adaptive, rather than universally ``clean'', imagery, in the new era of AI being the main data customer is highlighted.
- 4
- 4
- 4
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.