paper-with-me

Papers

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping

2021-05-14 · CVPR 2021 1 · Austin Stone, Daniel Maurer, Alper Ayvaci, Anelia Angelova, Rico Jonschkowski

We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2. Our method integrates architecture improvements from supervised optical flow, i.e. the RAFT model, with new ideas for unsupervised learning that include a sequence-aware self-supervision loss, a technique for handling out-of-frame motion, and an approach for learning effectively from multi-frame video data while still only requiring two frames for inference.

📄 PDF Abstract BibTeX arXiv:2105.07014

Code (3)

google-research/google-research/tree/master/smurf 공식 구현 jax
ChristophReich1996/SMURF pytorch
MindSpore-scientific/code-14/tree/main/smu mindspore

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning

2024-05-09 · Junzhi Chen, Juhao Liang, Benyou Wang

The emergence of large language models (LLMs) has opened up unprecedented possibilities for automating complex tasks that are often comparable to human performance. Despite their capabilities, LLMs still encounter diffic…

SMURFF: a High-Performance Framework for Matrix Factorization

2019-04-04 · Tom Vander Aa, Imen Chakroun, Thomas J. Ashby, Jaak Simm 외

Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting. Yet BMF is more computationally intensive and thus more c…

Activity PredictionRecommendation SystemsVocal Bursts Intensity Prediction

Searching for Smurfs: Testing if Money Launderers Know Alert Thresholds

2023-09-22 · Rasmus Ingemann Tuffveson Jensen, Joras Ferwerda, Christian Remi Wewer

To combat money laundering, banks raise and review alerts on transactions that exceed confidential thresholds. This paper presents a data-driven approach to detect smurfing, i.e., money launderers seeking to evade detect…

counterfactual

SMUDLP: Self-Teaching Multi-Frame Unsupervised Endoscopic Depth Estimation with Learnable Patchmatch

2022-05-30 · Shuwei Shao, Zhongcai Pei, Weihai Chen, Xingming Wu 외

Unsupervised monocular trained depth estimation models make use of adjacent frames as a supervisory signal during the training phase. However, temporally correlated frames are also available at inference time for many cl…

Depth Estimation

GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering

2025-06-04 · Bruno Deprez, Bart Baesens, Tim Verdonck, Wouter Verbeke

Money laundering poses a significant challenge as it is estimated to account for 2%-5% of the global GDP. This has compelled regulators to impose stringent controls on financial institutions. One prominent laundering met…

Computational EfficiencyFraud DetectionNetwork Embedding