用ViT+DETR提升国际象棋棋盘识别准确率
ChessQueries: Toward Better Chess Board Recognition
- 采用ViT编码器与DETR解码器结合的结构
- 在ChessReD上错误率降至0.01个/棋盘（旧方法3.4）
- 适用于真实比赛场景，适合棋类视觉研究者
棋盘识别旨在将棋盘图像映射为每个格子上的棋子信息。现有两个基准：ChessCog为合成数据，ChessReD来自单个棋局的手机拍摄图像。本文提出ChessQueries，结合ViT编码器与DETR风格解码器，显著优于现有方法。在ChessReD基准上，准确率从15.3%提升至99.2%，平均错误仅0.01个格子（此前SOTA为3.4和0.15）。该方法在分布外数据上表现稳健，已饱和两个数据集性能。此外，我们发布了一个从顶级国际象棋赛事转播中提取的新更难公开数据集（SLCC）。代码、模型权重及数据集将开源。
原文摘要 · Abstract (English)
Chess board recognition is the task of mapping the image of a chess board to the information of which piece is on which square. So far this task has two established benchmarks: ChessCog is synthetic, and ChessReD comes from smartphone pictures of a single chess board setup. We introduce ChessQueries, a new method combining a ViT encoder with a DETR-style decoder, which outperforms existing methods. On the ChessReD benchmark, we improve the state of the art from 15.3% to 99.2%, and demonstrate strong capabilities on out-of-distribution datasets. Our method saturates the task on the two datasets, with an average 0.01 wrong squares per board (vs. SotA: 3.4 / 0.15 respectively). We also share a new, harder public dataset, parsed from broadcasted top-level chess tournaments. Code, model weights and the SLCC data will be released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。