7 papers
Memory as Plans: World-Action Modeling with Memory-Grounded Planning
Sizhe Zhao, Haozhe Xie, Weiyu Zhao +5
Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inherently non-Markovian, requiring long-horizon memory beyond t…
TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
Sizhe Zhao, Shengping Zhang, Shuo Yang +3
Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size. We instead explore inference-time strategy as an altern…
RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
Marcos V. Conde, Radu Timofte, Radu Berdan +30
Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensiv…
Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis
Yipengjing Sun, Shengping Zhang, Chenyang Wang +3
We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that…
NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
Lei Sun, Andrea Alfarano, Peiqi Duan +85
This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal…
Technique Report of CVPR 2024 PBDL Challenges
Ying Fu, Yu Li, Shaodi You +96
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to info…
Dual-Context Aggregation for Universal Image Matting
Qinglin Liu, Xiaoqian Lv, Wei Yu +2
Natural image matting aims to estimate the alpha matte of the foreground from a given image. Various approaches have been explored to address this problem, such as interactive matt…