Scene Flow Estimation

Latest papers

12 papers4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Act4R: Action-conditioned 4D reconstruction for kinematics-free control
Oct 12, 2026Zhaoliang Zhang, Chenhao Yu, Zhimin Shao +2Scene Flow Estimation Vision-Based Robot Control
Department of Electrical and Computer Engineering Johns Hopkins University · Department of Data Science University of Virginia
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
Oct 7, 2026Jiuming Liu, Jianing Li, Mengmeng Liu +3Scene Flow Estimation Spatiotemporal Forecasting
University of Cambridge · Shanghai Jiao Tong University · University of Twente +1
DiFF: Doppler-informed Flow Matching for Human Motion Flow
Sep 30, 2026Kai Wang, Mingle ZhaoFlow Matching Scene Flow Estimation
AevaScenes: An FMCW LiDAR Dataset and Benchmark for Long-Range Perception
Sep 27, 2026Gautham Narayan Narasimhan, Heethesh Vhavle, Kumar Bhargav Viswanatha +2Scene Flow Estimation Lidar-Based 3D Object Detection
Aeva Inc., Mountain View, CA, USA. · Carnegie Mellon University, Pittsburgh, PA, USA.
UniQuery4R: Unified 4D Scene Reconstruction from a Single Query
Aug 18, 2026Tiancheng Chen, Sheng Tang, Wenhua Jin +4Scene Flow Estimation Dynamic Scene Reconstruction
Kosmo Research · Automotive Engineering Department, Jilin University · School of Software, Tsinghua University
CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation
Jul 31, 2026Minh-Quan Dao, Yancong Lin, Shiming Wang +2Scene Flow Estimation
Nantes Université, LS2N · University of Nottingham · TU Delft +1
DisFlow: Scene Flow from Distance Field for Object Pose, Velocity Tracking, and Dynamic Object Reconstruction
Jun 1, 2026Lan Wu, Sheila Sutjipto, Jennifer Wakulicz +1Scene Flow Estimation Visual Object Tracking
Robotics Institute, University of Technology Sydney, Ultimo, NSW 2007, Australia
RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow
Apr 21, 2026Xunpei Sun, Zuoxun Hou, Yi Chang +2Optical Flow Scene Flow Estimation
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 510006. · Beijing Institute of Space Mechanics and Electricity, Beijing, China 100094. · School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China 430074.
ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
Apr 2, 2026Yanzhe Liang, Ruijie Zhu, Hanzhi Chang +3Scene Flow Estimation Dynamic Scene Reconstruction
University of Science and Technology of China · National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory
PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
Mar 20, 2026Min Lin, Gangwei Xu, Xianqi Wang +2Scene Flow Estimation 3D Point Tracking
Huazhong University of Science and Technology · Optics Valley Laboratory
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Mar 3, 2026Jiahao Lu, Jiayi Xu, Wenbo Hu +5Scene Flow Estimation 3D Point Tracking
The Hong Kong University of Science and Technology · ARC Lab, Tencent PCG
TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
Feb 22, 2026Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu +4Scene Flow Estimation Self-Supervised Learning
KTH Royal Institute of Technology · Hong Kong University of Science and Technology · Scania +2

Oct 12, 2026J/K move · Enter open · S save

Act4R: Action-conditioned 4D reconstruction for kinematics-free control

Zhaoliang Zhang, Chenhao Yu, Zhimin Shao, Xijun Liu+1

Department of Electrical and Computer Engineering Johns Hopkins University · Department of Data Science University of Virginia

Scene Flow Estimation Vision-Based Robot Control 4D Reconstruction 4D Scene Understanding Robot Dynamics Learning

Open paper AskPDF arXiv

Precise control of movement across various robotic embodiments is a longstanding challenge. Modeling complex robotic structures requires significant time, dedicated sensors, and manual labeling. Recent advancements in 4D representation learning offer an interesting alternative: can we leverage 4D features lifted from 2D observations to densely map a robot's spatial movement based on the action signal? To this end, we propose Act4R, a framework that builds on 3D foundation model to predict a robot's 3D scene flow with any given action. Act4R introduces a Spatial-Action Encoder, which encodes the current 2D robot state and its action signals into embeddings that represent future robot state in 3D. Then, both the current and future spatial embeddings are decoded into point maps to estimate action-conditioned scene flow. To effectively learn the mapping between action and future state, Act4R introduces spatial-action fusion in its transformer-based encoder, and a spatial alignment loss that guides the encoder for future flow prediction. After training on some samples of a given embodiment, Act4R can perform inverse control by optimizing the signal to achieve the desired scene flow. We evaluate Act4R on a public real-world dataset and synthetic data collected in simulator. Experiments on various robotic platforms show that Act4R outperforms the previous SoTA in scene flow prediction. Our method also performs better in inverse control, both on the action accuracy metric and in closed-loop control in simulation.