RealD$^2$iff: Bridging Real-World Gap in Robot Manipulation via Depth Diffusion

• URL: http://arxiv.org/abs/2511.22505v1
• Date: Thu, 27 Nov 2025 14:36:56 GMT
• Title: RealD$^2$iff: Bridging Real-World Gap in Robot Manipulation via Depth Diffusion
• Authors: Xiujian Liang, Jiacheng Liu, Mingyang Sun, Qichen He, Cewu Lu, Jianhua Sun,
• Abstract summary: We propose a clean-to-noisy paradigm that learns to synthesize noisy depth.<n>We introduce RealD$2$iff, a hierarchical coarse-to-fine diffusion framework.<n>We provide empirical and experimental validation demonstrating the effectiveness of this paradigm.
• Score: 48.86480272116588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by the denoising capability of diffusion models, we invert the conventional perspective and propose a clean-to-noisy paradigm that learns to synthesize noisy depth, thereby bridging the visual sim2real gap through purely simulation-driven robotic learning. Building on this idea, we introduce RealD$^2$iff, a hierarchical coarse-to-fine diffusion framework that decomposes depth noise into global structural distortions and fine-grained local perturbations. To enable progressive learning of these components, we further develop two complementary strategies: Frequency-Guided Supervision (FGS) for global structure modeling and Discrepancy-Guided Optimization (DGO) for localized refinement. To integrate RealD$^2$iff seamlessly into imitation learning, we construct a pipeline that spans six stages. We provide comprehensive empirical and experimental validation demonstrating the effectiveness of this paradigm. RealD$^2$iff enables two key applications: (1) generating real-world-like depth to construct clean-noisy paired datasets without manual sensor data collection. (2) Achieving zero-shot sim2real robot manipulation, substantially improving real-world performance without additional fine-tuning.

Related papers

• DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer [62.18680935878919]
  We introduce DiffusionHarmonizer, an online generative enhancement framework that transforms renderings into temporally consistent outputs.<n>At its core is a single-step temporally-conditioned enhancer capable of running in online simulators on a single GPU.
  arXiv  Detail & Related papers  (2026-02-27T15:35:30Z)
• DeFM: Learning Foundation Representations from Depth for Robotics [49.77188649197404]
  We present DeFM, a self-supervised foundation model trained entirely on depth images for robotic applications.<n>DeFM learns geometric and semantic representations that generalize to diverse environments, tasks, and sensors.<n>It achieves state-of-the-art performance and demonstrates strong generalization from simulation to real-world environments.
  arXiv  Detail & Related papers  (2026-01-26T19:45:31Z)
• R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation [74.41728218960465]
  We propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data.<n>R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.
  arXiv  Detail & Related papers  (2025-10-09T17:55:44Z)
• Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns [4.977925450373957]
  We propose a novel TripleGAN framework for training super-resolution reconstruction models.<n>The framework learns real-world degradation patterns from LR observations and synthesizes datasets with corresponding degradation characteristics.<n>Our method exhibits clear advantages in quantitative metrics while maintaining sharp reconstructions without over-smoothing artifacts.
  arXiv  Detail & Related papers  (2025-06-20T14:24:48Z)
• Real-World Remote Sensing Image Dehazing: Benchmark and Baseline [19.747354924759104]
  The scarcity of real-world remote sensing hazy image pairs has compelled existing methods to rely primarily on synthetic datasets.<n>We introduce Real-World Remote Sensing Hazy Image dataset (RRSHID), the first large-scale dataset featuring real-world hazy and dehazed image pairs.<n>Based on this, we propose MCAF-Net, a novel framework tailored for real-world RSID.
  arXiv  Detail & Related papers  (2025-03-23T07:15:46Z)
• HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection [4.908389661988192]
  HFMF is a comprehensive two-stage deepfake detection framework.<n>It integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism.<n>We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T00:20:29Z)
• RPMArt: Towards Robust Perception and Manipulation for Articulated Objects [56.73978941406907]
  We propose a framework towards Robust Perception and Manipulation for Articulated Objects ( RPMArt) RPMArt learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. We introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer.
  arXiv  Detail & Related papers  (2024-03-24T05:55:39Z)
• Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution [81.74583887661794]
  We build a new real-world super-resolution benchmark with both integer and non-integer scaling factors. We propose a Dual-level Deformable Implicit Representation (DDIR) to solve real-world scale arbitrary super-resolution. Our trained model achieves state-of-the-art performance on the RealArbiSR and RealSR benchmarks for real-world scale arbitrary super-resolution.
  arXiv  Detail & Related papers  (2024-03-16T13:44:42Z)
• Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs [59.12526668734703]
  We introduce Composable Object Volume NeRF (COV-NeRF), an object-composable NeRF model that is the centerpiece of a real-to-sim pipeline. COV-NeRF extracts objects from real images and composes them into new scenes, generating photorealistic renderings and many types of 2D and 3D supervision.
  arXiv  Detail & Related papers  (2024-03-07T00:00:02Z)
• Rethinking Blur Synthesis for Deep Real-World Image Deblurring [4.00114307523959]
  We propose a novel realistic blur synthesis pipeline to simulate the camera imaging process. We develop an effective deblurring model that captures non-local dependencies and local context in the feature domain simultaneously. A comprehensive experiment on three real-world datasets shows that the proposed deblurring model performs better than state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-09-28T06:50:16Z)

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.