RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
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 evaluation loop. We systematically examine the consequences of this overlooked design choice across five fundamental ISP dimensions: gain, sensor noise, chromatic response, tonal response, and bit depth.
초록에서 가져왔습니다. 요약을 준비 중입니다.