AI RESEARCH
BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression
arXiv CS.CV
•
ArXi:2605.29583v1 Announce Type: new High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information (e.g., ownership, provenance, and authentication codes), enabling reliable identification and integrity verification in large-scale 3D asset pipelines. Existing bit-to-token watermarking methods based on a pre-trained text encoder are limited to 77-bit messages due to CLIP's fixed 77-token context length, as tokens beyond this limit are uned by learned positional embeddings. To address this limitation, we.