Research Analyzer
← Back ICRA 2026

FlowDreamer: A RGB-D World Model with Flow-Based Motion Representations for Robot Manipulation

Jun Guo, Xiaojian Ma, Yikai Wang, Min Yang, Huaping Liu, Qing Li

PDF

AI summary

Explicitly modeling 3D scene flow as an intermediate motion representation significantly boosts future frame prediction accuracy and robot manipulation success rates.
RGB-D world models 3D scene flow robot manipulation diffusion models visual planning dynamics prediction

Problem

Current RGB-D world models merge dynamics prediction and visual rendering into a single network, which obscures physical motion understanding and degrades prediction performance by prioritizing visual fidelity over accurate dynamics.

Approach

FlowDreamer decouples the task into two stages: a U-Net explicitly predicts 3D scene flow to capture motion dynamics, which then conditions a diffusion model to generate future RGB-D frames, all trained end-to-end.

Key results

  • 7% improvement in semantic similarity on video prediction benchmarks
  • 11% gain in pixel quality metrics across RT-1 and Language Table datasets
  • 6% increase in robot manipulation success rates on visual planning tasks
  • Demonstrates superior dynamics modeling over single-stage and separately trained baselines

Why it matters

Enables more reliable and interpretable robot simulators for planning and control, reducing reliance on precise physical modeling in real-world manipulation.

Abstract

This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that operate on RGB-D frames (RGB-D world models). As opposed to canonical approaches that handle dynamics prediction mostly implicitly and reconcile it with visual rendering in a single model, we introduce FlowDreamer, which adopts 3D scene flow as explicit motion representations. FlowDreamer first predicts 3D scene flow from the past frame and action conditions with a U-Net, and then a diffusion model will predict the future frame utilizing the scene flow. FlowDreamer is trained end-to-end despite its modularized nature. We conduct experiments on 4 different benchmarks, covering both video prediction and visual planning tasks. The results demonstrate that FlowDreamer achieves better performance compared to other baseline RGB-D world models by 7% on semantic similarity, 11% on pixel quality, and 6% on success rate in various robot manipulation domains.

Index terms

Deep Learning in Grasping and Manipulation Visual Learning Deep Learning Methods

Related papers