Flow reversal improves temporal generation quality with conditional sources
Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matching
Computer Vision and Pattern Recognition
Summary
Generating sequences like videos or robot motions often requires simulating changes over time, starting from random noise. The authors present a way to better choose this starting noise based on the specific point in time, by learning it backward from the output. This approach improves quality and efficiency when creating videos or planning robot motions. They show it works well in several tasks involving video prediction, interpolation, and robot control.
What this means in practice
- •For video processing engineers: Generate higher-quality video predictions and interpolations with fewer computations by using learned conditional noise distributions.
- •For robotics system developers: Improve the generation of robot motion plans for tasks with seven degrees of freedom by employing flow reversal to learn source distributions.
Authors
Kuan-Hsun Tu, Hsuan-Chi Liu, Jia-Wei Liao, Chien-Sheng Chiang, Tsung-Wei Ke
Abstract
We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas standard conditional flow matching (FM) incorporates conditioning through the vector field and draws source samples from a standard Gaussian, CNP-Flow uses a conditional noise predictor (CNP) to produce an isotropic Gaussian source for each temporal condition. The CNP is supervised by source samples obtained through flow reversal, which maps observed targets backward through a pretrained FM model. A three-stage pipeline pretrains the FM model, trains the CNP, and fine-tunes the FM model using the learned source distribution, while preserving the FM backbone architecture. Across video prediction, video interpolation, and 7-DoF Franka robot motion planning, CNP-Flow consistently improves generation quality. It also matches baseline performance with fewer function evaluations. Project page: https://embodiedai-ntu.github.io/cnpflow