1 citations · 1 across the 13 of their papers we have counts for
14 papers
Weather-Conditioned Depth Anything
Zhaoming Xu, Chan-Wei Hu, Kuan-Ru Huang +4
Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, they still suffer from critic…
4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation
Zihao Zhu, Kuan-Ru Huang, Zhaoming Xu +6
High-resolution datasets are essential for advancing super-resolution (SR) and text-to-image (T2I) diffusion research. However, current publicly available datasets lack both the na…
Training a Student Expert via Semi-Supervised Foundation Model Distillation
Pardis Taghavi, Tian Liu, Renjie Li +2
Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervis…
PISCO: Precise Video Instance Insertion with Sparse Control
Xiangbo Gao, Renjie Li, Xinghao Chen +4
The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engineering and "cherry-picking" - towards…
HeadsUp! High-Fidelity Portrait Image Super-Resolution
Renjie Li, Zihao Zhu, Xiaoyu Wang +1
Portrait pictures, which typically feature both human subjects and natural backgrounds, are one of the most prevalent forms of photography on social media. Existing image super-res…
SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling
Fanjiang Ye, Zepeng Zhao, Yi Mu +11
Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is r…
MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding
Renjie Li, Ruijie Ye, Mingyang Wu +4
Humans are integral components of the transportation ecosystem, and understanding their behaviors is crucial to facilitating the development of safe driving systems. Although recen…
4KAgent: Agentic Any Image to 4K Super-Resolution
Yushen Zuo, Qi Zheng, Mingyang Wu +10
We present 4KAgent, a unified agentic super-resolution generalist system designed to universally upscale any image to 4K resolution (and even higher, if applied iteratively). Our s…
VISTA: Generative Visual Imagination for Vision-and-Language Navigation
Yanjia Huang, Mingyang Wu, Renjie Li +1
Vision-and-Language Navigation (VLN) tasks agents with locating specific objects in unseen environments using natural language instructions and visual cues. Many existing VLN appro…
NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results
Nikolay Safonov, Alexey Bryncev, Andrey Moskalenko +28
This paper presents an overview of the NTIRE 2025 Challenge on UGC Video Enhancement. The challenge constructed a set of 150 user-generated content videos without reference ground…
CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Pardis Taghavi, Tian Liu, Renjie Li +2
Instance segmentation demands costly per-pixel annotations and computationally expensive models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that c…
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
Xin Li, Kun Yuan, Bingchen Li +110
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Qualit…
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
Bin Ren, Hang Guo, Lei Sun +143
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep mode…
PANDORA: Diffusion Policy Learning for Dexterous Robotic Piano Playing
Yanjia Huang, Renjie Li, Zhengzhong Tu
We present PANDORA, a novel diffusion-based policy learning framework designed specifically for dexterous robotic piano performance. Our approach employs a conditional U-Net archit…