39 pages, 27 figures; a shorter version of this paper was acceppted at the ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling
Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, Consistency Models (CMs) have emerged to address this challenge by approximating the integral of the PF ODE, largely reducing the number of iterations. Yet, the absence of an explicit ODE solver complicates the inversion process. To resolve this, we introduce Bidirectional Consistency Model (BCM), which learns a single neural network that enables both forward and backward traversal along the PF ODE, efficiently unifying generation and inversion tasks within one framework. We can train BCM from scratch or tune it using a pretrained consistency model, which reduces the training cost and increases scalability. We demonstrate that BCM enables one-step generation and inversion while also allowing the use of additional steps to enhance generation quality or reduce reconstruction error. We further showcase BCM's capability in downstream tasks, such as interpolation and inpainting. Our code and weights are available at https://github.com/Mosasaur5526/BCM-iCT-torch.
Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation
School of Software Engineering, Xi'an Jiaotong University(西安交通大学软件工程学院);School of Computer and Information Science, Hefei University of Technology(合肥工业大学计算机与信息科学学院);Faculty of Science and Technology, University of Macau(澳门大学科技学院)
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学研究所);Beijing Key Laboratory of Advanced Information Science and Network Technology(北京市先进信息科学与网络技术重点实验室);NLPR, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学)
Recovering Partially Corrupted Objects via Sketch-Guided Bidirectional Feature Interaction
School of Electrical and Data Engineering(电气与数据工程学院);Australian Artificial Intelligence Institute(澳大利亚人工智能研究所);University of Technology Sydney(悉尼科技大学);School of Computer Science and Information Engineering(计算机科学与信息工程学院);Hefei University of Technology(合肥工业大学)
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
State Key Laboratory for Novel Software Technology(新型软件技术国家重点实验室);Tencent Hunyuan(腾讯文英);Shanghai Jiao Tong University(上海交通大学);Renmin University of China(中国人民大学);Tsinghua University(清华大学);Shanghai AI Lab(上海人工智能实验室)
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Institute of Science and Technology for Brain-Inspired Intelligence(脑启发智能科学与技术研究院);Fudan University(复旦大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);IEG, Tencent Inc.(腾讯IEG)