[2510.01478] Purrception: Variational Flow Matching for Vector-Quantized Image Generation

Computer Science > Computer Vision and Pattern Recognition arXiv:2510.01478 (cs) [Submitted on 1 Oct 2025 (v1), last revised 1 Mar 2026 (this version, v3)] Title:Purrception: Variational Flow Matching for Vector-Quantized Image Generation Authors:Răzvan-Andrei Matişan, Vincent Tao Hu, Grigory Bartosh, Björn Ommer, Cees G. M. Snoek, Max Welling, Jan-Willem van de Meent, Mohammad Mahdi Derakhshani, Floor Eijkelboom View a PDF of the paper titled Purrception: Variational Flow Matching for Vector-Quantized Image Generation, by R\u{a}zvan-Andrei Mati\c{s}an and 8 other authors View PDF Abstract:We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous transport dynamics. Our method adapts Variational Flow Matching to vector-quantized latents by learning categorical posteriors over codebook indices while computing velocity fields in the continuous embedding space. This combines the geometric awareness of continuous methods with the discrete supervision of categorical approaches, enabling uncertainty quantification over plausible codes and temperature-controlled generation. We evaluate Purrception on ImageNet-1k 256x256 generation. Training converges faster than both continuous flow matching and discrete flow matching baselines while achieving competitive FID scores with state-of-the-art models. This demonstrates that Variational Flow Matching can effectively bri...