3 papers
cs.CV2025
RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark
Ziteng Cui, Jianfei Yang, Tatsuya Harada
In the computer vision community, the preference for pre-training visual models has largely shifted toward sRGB images due to their ease of acquisition and compact storage. However…
cs.CV2025
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…
cs.CV2024
NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
Tao Wu, Chuhao Zhou, Yen Heng Wong +2
The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language unde…