Results for “stereo-depth-estimation”

Evaluates the trade-off between file size reduction and image fidelity when encoding radio astronomy data using JPEG2000, benchmarking both lossless and lossy compression modes to determine the compression ratio at which visual artifacts first appear.

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Inspects metadata, hidden channels, and appended payloads in media files to recover concealed data in steganography challenges.