Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Gestalt Principles of Perception01:21

Gestalt Principles of Perception

362
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
362
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

128
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
128

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2022
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Aug 3, 2025

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

2.2K

Physics-Informed Guided Disentanglement in Generative Networks.

Fabio Pizzati, Pietro Cerri, Raoul de Charette

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 7, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a framework to improve image-to-image translation (i2i) by disentangling visual traits using physics models or neural networks. This enhances translation quality, controllability, and variability in challenging scenarios.

    More Related Videos

    Generating Strictly Controlled Stimuli for Figure Recognition Experiments
    05:39

    Generating Strictly Controlled Stimuli for Figure Recognition Experiments

    Published on: March 18, 2019

    5.3K
    Using Generative Art to Convey Past and Future Climate Transitions
    06:10

    Using Generative Art to Convey Past and Future Climate Transitions

    Published on: March 31, 2023

    1.0K

    Related Experiment Videos

    Last Updated: Aug 3, 2025

    Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
    10:44

    Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

    Published on: December 7, 2021

    2.2K
    Generating Strictly Controlled Stimuli for Figure Recognition Experiments
    05:39

    Generating Strictly Controlled Stimuli for Figure Recognition Experiments

    Published on: March 18, 2019

    5.3K
    Using Generative Art to Convey Past and Future Climate Transitions
    06:10

    Using Generative Art to Convey Past and Future Climate Transitions

    Published on: March 31, 2023

    1.0K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Physics-Informed Machine Learning

    Background:

    • Image-to-image translation (i2i) networks face challenges with entanglement effects, especially when physics-related phenomena like occlusions or fog are present in the target domain.
    • These entanglement effects degrade translation quality, reduce controllability, and limit variability in generated images.

    Purpose of the Study:

    • To propose a general framework for disentangling visual traits in target images for improved i2i.
    • To enhance the quality, controllability, and variability of i2i networks by addressing entanglement effects.

    Main Methods:

    • Developed a framework utilizing simple physics models to guide disentanglement, rendering some target traits physically and learning others.
    • Introduced neural-guided disentanglement as an alternative when physical models are inaccessible, using generative networks.
    • Proposed three disentanglement strategies: fully differentiable physics model, partially non-differentiable physics model, and neural network guidance.

    Main Results:

    • The proposed physical models, optimally regressed on target data, enable controllable generation of unseen scenarios.
    • The framework demonstrates versatility across different guidance strategies (physics-based and neural-guided).
    • Disentanglement strategies significantly improve i2i performance both qualitatively and quantitatively in complex scenarios.

    Conclusions:

    • The framework effectively disentangles visual traits in i2i, overcoming limitations posed by physics-related phenomena.
    • Physics-guided and neural-guided disentanglement offer robust solutions for enhancing i2i translation quality and control.
    • This approach opens new avenues for controllable and high-fidelity image generation.