355 citations · 2.7k across the 325 of their papers we have counts for
46 papers · 2 filters
Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark
Yuedong Tan, Lei Qi, Yu Liu +13
Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conf…
LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder
Andrei Arhire, Mihaela-Elena Breabăn, Radu Timofte
We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise decoder. LightMIS aligns th…
Benchmarking RAW and RGB Restoration in Image Signal Processors
Zihao Lu, Radu Timofte, Marcos V. Conde
Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A)…
Elastic Token Compression for Pixel-Space Diffusion Transformers
Eduard Zamfir, Christian Reisswig, Zongwei Wu +2
Natural images concentrate their detail in a small fraction of the frame, yet diffusion models spend a full token on every patch, in every layer and at every timestep. The waste is…
Glass Surface Detection Grounded in 3D Visual Geometry
Yiwei Lu, Ke Xu, Tao Yan +3
Glass surface detection (GSD) is critical for scene understanding and reconstruction, and yet remains challenging due to the transparency and reflectivity of glass surfaces. Existi…
When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation
Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu +1
Semantic segmentation demands a careful balance between accuracy, efficiency, and scalability, which remains difficult to achieve for high-resolution imagery. Convolutional network…
Multiple Scale Latents for Learned Image Compression
Jonas Brenig, Radu Timofte
Most learned image compression systems rely on a single latent representation combined with a hyperprior, which limits their ability to efficiently capture image structure across s…
Mixture-of-Experts-based Entropy Model for Learned Image Compression
Jonas Brenig, Radu Timofte
Learned image compression has seen significant progress in recent years with the development of end-to-end learned models that achieve better compression efficiency than state-of-t…
NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge
Aleksei Khalin, Egor Ershov, Artyom Panshin +46
This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of misaligned smartphone images…
Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search
Saif U Din, Muhammad Ahsan Hussain, Radu Timofte +1
Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: INT8 TensorFlow Lite export, d…
TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution
Sicheng Gao, Zhuyun Zhou, Yixuan Liu +3
Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due to the quadratic computationa…
The RealDefocus Benchmark for Defocus Deblurring
Tim Seizinger, Zhuyun Zhou, Radu Timofte
Single-Image Defocus Deblurring (SIDD) aims to recover an all-in-focus image from a single defocused observation, but rigorous and reproducible evaluation remains challenging due t…
Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis
Anujaya Vijayakumar, Radu Timofte, Dmitry Ignatov
Introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for LLM-based neural architecture search (NAS). Usi…
The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results
Lei Sun, Hang Guo, Bin Ren +6
This paper reports on the NTIRE 2026 Challenge on Image Denoising, specifically focusing on the high-noise regime (). The competition investigates advanced neural architectu…
Low Light Image Enhancement Challenge at NTIRE 2026
George Ciubotariu, Sharif S M A, Abdur Rehman +90
This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this cha…
NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Suhang Yao +95
This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this c…
The First Controllable Bokeh Rendering Challenge at NTIRE 2026
Tim Seizinger, Florin-Alexandru Vasluianu, Jeffrey Chen +23
This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants r…
Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs
Faraz Kayani, Sarmad Kayani, Asad Ahmed +2
While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibilit…
deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal
Lorenzo Beltrame, Jules Salzinger, Filip Svoboda +4
Shadows cast by terrain and tall structures remain a major obstacle for high-resolution satellite image analysis, degrading classification, detection, and 3D reconstruction perform…
NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results
Jiebin Yan, Chenyu Tu, Weixia Zhang +8
This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This…
Specialist-Generalist Fusion with Outcome-Supervised Rationales for Deepfake Detection
Benedikt Hopf, Zongwei Wu, Radu Timofte
Generalizable deepfake detection requires complementary forensic and semantic visual evidence. Specialist encoders capture subtle manipulation traces but can overfit to source-spec…
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
Shuhong Liu, Chenyu Bao, Ziteng Cui +103
This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to…
NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Report
Andrei Dumitriu, Aakash Ralhan, Florin Miron +32
This report presents the NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge, which targets automatic rip current understanding in images. Rip currents are haza…
Robust Deepfake Detection, NTIRE 2026 Challenge: Report
Benedikt Hopf, Radu Timofte, Chenfan Qu +54
Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight imag…