ChessQueries: Toward Better Chess Board Recognition
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors worked on making a computer better at looking at pictures of chess boards and figuring out which pieces are on each square. They created a new method called ChessQueries that uses a special type of neural network and is much more accurate than previous ones. On one popular test with real smartphone images, their method went from about 15% accuracy to over 99%. They also made a new, tougher dataset using images from professional chess tournaments to help future research.
Chess board recognitionViT encoderDETR decoderChessReD benchmarkSynthetic datasetsOut-of-distribution datasetsNeural networksImage recognitionDatasetComputer vision
Authors
Joël Seytre
Abstract
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.