9 papers
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
Shuhong Liu, Heng Zhou, Lingfeng Qian +7
Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and e…
FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
Shuhong Liu, Xining Ge, Ziteng Cui +8
Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution a…
Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis
Ziteng Cui, Shuhong Liu, Xiaoyu Dong +4
High-quality image acquisition in real-world environments remains challenging due to complex illumination variations and inherent limitations of camera imaging pipelines. These iss…
RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction
Shuhong Liu, Chenyu Bao, Ziteng Cui +11
We introduce RealX3D, a real-capture benchmark for multi-view visual restoration and 3D reconstruction under diverse physical degradations. RealX3D groups corruptions into four fam…
Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
Shuhong Liu, Xining Ge, Ziying Gu +7
Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts but largely leave stochastic noise unres…
Perception-Inspired Color Space Design for Photo White Balance Editing
Yang Cheng, Ziteng Cui, Shenghan Su +2
White balance (WB) is a key step in the image signal processor (ISP) pipeline that mitigates color casts caused by varying illumination and restores the scene's true colors. Curren…
ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"
Zhongyi Zhou, Kohei Uehara, Haoyu Zhang +5
Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable anno…
Emergence of Painting Ability via Recognition-Driven Evolution
Yi Lin, Lin Gu, Ziteng Cui +5
From Paleolithic cave paintings to Impressionism, human painting has evolved to depict increasingly complex and detailed scenes, conveying more nuanced messages. This paper attempt…
Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design
Junjie Zhang, Zhimin Zong, Lin Gu +8
The evolution of colour vision is captivating, as it reveals the adaptive strategies of extinct species while simultaneously inspiring innovations in modern imaging technology. In…