SciFlow: Semantic Cross Interference for Self-Supervised Optical Flow Domain Generalization

• URL: http://arxiv.org/abs/2606.29004v1
• Date: Sat, 27 Jun 2026 16:37:51 GMT
• Title: SciFlow: Semantic Cross Interference for Self-Supervised Optical Flow Domain Generalization
• Abstract summary: SciFlow is a network-agnostic, training-based approach to generalize motion estimation across synthetic and open-world domains.<n>Our experiment results show that SciFlow not only significantly enhances model robustness amidst domain variations, but also remarkably enables synthetic-to-real domain generalization without requiring any ground truth in the open world.
• Score: 55.19058866002113
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Motions of objects and scenes carry essential intelligence in video understanding, offering rich cues for interpreting dynamic settings and interactions. Due to the cost and scarcity of high-quality annotation or ground truth of pixel-wise optical flow, however, motion estimation models are typically trained in synthetic domains while deployed in real-world domains. Addressing synthetic-to-real domain generalization challenges has been crucial for developing practical solutions in diverse open-world use cases. This paper introduces SciFlow, a simple yet effective, network-agnostic, training-based approach that leverages self-supervised learning to generalize motion estimation across synthetic and open-world domains. Specifically, SciFlow imposes semantic interference from open-world images onto synthetic images during training, blending indomain features with cross-domain interference, which enables the network to adapt to the real-world domains. Additionally, SciFlow utilizes geometric consistency to ensure validity of the self-supervision. Our experiment results show that SciFlow not only significantly enhances model robustness amidst domain variations, but also remarkably enables synthetic-to-real domain generalization without requiring any ground truth in the open world.

Related papers

• HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models [50.18051979020699]
  End-to-end autonomous driving has emerged as a compelling alternative to traditional modular pipelines.<n>We propose a trajectory-driven learning paradigm that organizes training around planning trajectories.<n>We show that a single unified model can be trained on heterogeneous datasets while maintaining strong performance within each domain.
  arXiv  Detail & Related papers  (2026-05-19T10:12:01Z)
• SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance [49.69016078147708]
  Accurately reconstructing human behavior in close-interaction scenarios is crucial for enabling realistic virtual interactions in augmented reality.<n>We propose SocialMirror, a diffusion-based framework that integrates semantic and geometric cues to effectively address these issues.<n>SocialMirror achieves state-of-the-art performance in reconstructing interactive human meshes, demonstrating strong generalization across unseen datasets and in-the-wild scenarios.
  arXiv  Detail & Related papers  (2026-04-15T07:41:52Z)
• Structured prototype regularization for synthetic-to-real driving scene parsing [7.087302867255982]
  Driving scene parsing is critical for autonomous vehicles to operate reliably in real-world traffic environments.<n>To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have become a popular alternative.<n>Models trained on synthetic data often perform poorly when applied to real-world scenes due to the synthetic-to-real domain gap.
  arXiv  Detail & Related papers  (2026-03-17T03:05:28Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation [7.099012213719071]
  This work introduces a semantic segmentation method based on latent diffusion models, termed Inter-Coder Connected Latent Diffusion (ICCLD)<n>ICCLD outperforms state-of-the-art UDA methods, achieving mIoU scores of 74.4 (GTA5$rightarrow$Cityscapes) and 67.2 ( Synthia$rightarrow$Cityscapes)
  arXiv  Detail & Related papers  (2024-12-22T04:55:41Z)
• Generalizing Event-Based Motion Deblurring in Real-World Scenarios [62.995994797897424]
  Event-based motion deblurring has shown promising results by exploiting low-latency events. We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur. A two-stage self-supervised learning scheme is then developed to fit real-world data distribution.
  arXiv  Detail & Related papers  (2023-08-11T04:27:29Z)
• Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts [133.99270341855728]
  Real-world domain styles can vary substantially due to environment changes and sensor noises. Deep models only know the training domain style. We propose Normalization Perturbation to overcome this domain style overfitting problem.
  arXiv  Detail & Related papers  (2022-11-08T17:36:49Z)
• Content Disentanglement for Semantically Consistent Synthetic-to-RealDomain Adaptation in Urban Traffic Scenes [39.38387505091648]
  Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. Deep learning techniques trained solely on synthetic data encounter dramatic performance drops when they are tested on real data. We propose a new, unsupervised, end-to-end domain adaptation network architecture that enables semantically consistent domain adaptation between synthetic and real data.
  arXiv  Detail & Related papers  (2021-05-18T17:42:26Z)
• Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks [12.282277258055542]
  We show that a deep attention convolutional neural network (DACNN) with specific visual sensor configuration performs as well as training on a dataset with high domain and parameter variation at lower computational complexity. Our new architecture adapts perception with respect to the control objective, resulting in zero-shot learning without pre-training a perception network.
  arXiv  Detail & Related papers  (2020-01-02T19:41:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.