mlsanityData to 14 Oct 2026

SRFlow: A Dataset and Regularization Model for High-Resolution Facial Optical Flow via Splatting Rasterization

arXiv 2601.06479 ↗First posted 10 Jan 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Facial optical flow supports a wide range of tasks in facial motion analysis. However, the lack of high-resolution facial optical flow datasets has hindered progress in this area. In this paper, we introduce Splatting Rasterization Flow (SRFlow), a high-resolution facial optical flow dataset, and Splatting Rasterization Guided FlowNet (SRFlowNet), a facial optical flow model with tailored regularization losses. These losses constrain flow predictions using masks and gradients computed via difference or Sobel operator. This effectively suppresses high-frequency noise and large-scale errors in texture-less or repetitive-pattern regions, enabling SRFlowNet to be the first model explicitly capable of capturing high-resolution skin motion guided by Gaussian splatting rasterization. Experiments show that training with the SRFlow dataset improves facial optical flow estimation across various optical flow models, reducing end-point error (EPE) by up to 42% (from 0.5081 to 0.2953). Furthermore, when coupled with the SRFlow dataset, SRFlowNet achieves up to a 48% improvement in F1-score (from 0.4733 to 0.6947) on a composite of three micro-expression datasets. These results demonstrate the value of advancing both facial optical flow estimation and micro-expression recognition.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 10 Jan 2026.

Builds on

23 of 42 references.

References · 23

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  3. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  5. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  6. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  7. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
  8. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 224
  9. 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 194
  10. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  11. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  12. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
11 more
  1. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  2. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  3. 2022Global Matching with Overlapping Attention for Optical Flow Estimationcited by 64
  4. 2022SKFlow: Learning Optical Flow with Super Kernelscited by 56
  5. 2024MemFlow: Optical Flow Estimation and Prediction with Memorycited by 55
  6. 2022Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithmscited by 51
  7. 2025DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Frameworkcited by 30
  8. 2023CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoningcited by 15
  9. 2024FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Modelcited by 7
  10. 2019Optical Flow Techniques for Facial Expression Analysis -- a Practical Evaluation Studycited by 6
  11. 2021Self-Supervised Approach for Facial Movement Based Optical Flowcited by 3

Built on by

Not cited yet.