Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

• URL: http://arxiv.org/abs/2509.02530v1
• Date: Tue, 02 Sep 2025 17:29:38 GMT
• Title: Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
• Abstract summary: Camera Depth Models (CDMs) are a simple plugin on daily-use depth cameras.<n>We develop a neural data engine that generates high-quality paired data from simulation by modeling a depth camera's noise pattern.<n>For the first time, our experiments demonstrate, for the first time, that a policy trained on raw simulated depth, without the need for adding noise or real-world fine-tuning, generalizes seamlessly to real-world robots.
• Score: 55.43376513158555
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modern robotic manipulation primarily relies on visual observations in a 2D color space for skill learning but suffers from poor generalization. In contrast, humans, living in a 3D world, depend more on physical properties-such as distance, size, and shape-than on texture when interacting with objects. Since such 3D geometric information can be acquired from widely available depth cameras, it appears feasible to endow robots with similar perceptual capabilities. Our pilot study found that using depth cameras for manipulation is challenging, primarily due to their limited accuracy and susceptibility to various types of noise. In this work, we propose Camera Depth Models (CDMs) as a simple plugin on daily-use depth cameras, which take RGB images and raw depth signals as input and output denoised, accurate metric depth. To achieve this, we develop a neural data engine that generates high-quality paired data from simulation by modeling a depth camera's noise pattern. Our results show that CDMs achieve nearly simulation-level accuracy in depth prediction, effectively bridging the sim-to-real gap for manipulation tasks. Notably, our experiments demonstrate, for the first time, that a policy trained on raw simulated depth, without the need for adding noise or real-world fine-tuning, generalizes seamlessly to real-world robots on two challenging long-horizon tasks involving articulated, reflective, and slender objects, with little to no performance degradation. We hope our findings will inspire future research in utilizing simulation data and 3D information in general robot policies.

Related papers

• Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator [70.34667754804168]
  Embodied navigation aims to build agents that interpret multimodal goals, reason in 3D space, and reach target destinations reliably in the real world.<n>We introduce Image2Sim, a real-time neural simulation framework that constructs high-quality interactive environments from posed RGB-D image sequences.
  arXiv  Detail & Related papers  (2026-07-07T02:42:41Z)
• 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)
• Masked Depth Modeling for Spatial Perception [44.0326843862591]
  LingBot-Depth is a depth completion model that refines depth maps through masked depth modeling.<n>It outperforms top-tier RGB-D cameras in terms of both depth precision and pixel coverage.<n>We release the code, checkpoint, and 3M RGB-depth pairs to the community of spatial perception.
  arXiv  Detail & Related papers  (2026-01-25T16:13:49Z)
• Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting [64.64738535860351]
  We present a scalable pipeline that converts single-view images into comprehensive, scale- and appearance-realistic 3D representations.<n>Our method bridges the gap between the vast repository of imagery and the increasing demand for spatial scene understanding.<n>By automatically generating authentic, scale-aware 3D data from images, we significantly reduce data collection costs and open new avenues for advancing spatial intelligence.
  arXiv  Detail & Related papers  (2025-07-24T14:53:26Z)
• ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulation [18.140839442955485]
  We develop a vision transformer-based algorithm for stereo depth recovery of transparent objects.<n>Our method incorporates a parameter-aligned, domain-adaptive, and physically realistic Sim2Real simulation for efficient data generation.<n>Our experimental results demonstrate the model's exceptional Sim2Real generalizability in real-world scenarios.
  arXiv  Detail & Related papers  (2024-09-13T15:44:38Z)
• LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
  multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks.<n>In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations.<n>We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)
• ImageManip: Image-based Robotic Manipulation with Affordance-guided Next View Selection [10.162882793554191]
  3D articulated object manipulation is essential for enabling robots to interact with their environment. Many existing studies make use of 3D point clouds as the primary input for manipulation policies. RGB images offer high-resolution observations using cost effective devices but lack spatial 3D geometric information. This framework is designed to capture multiple perspectives of the target object and infer depth information to complement its geometry.
  arXiv  Detail & Related papers  (2023-10-13T12:42:54Z)
• A Universal Semantic-Geometric Representation for Robotic Manipulation [42.18087956844491]
  We present $textbfSemantic-Geometric Representation (textbfSGR)$, a universal perception module for robotics. SGR leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning. Our experiments demonstrate that SGR empowers the agent to successfully complete a diverse range of simulated and real-world robotic manipulation tasks.
  arXiv  Detail & Related papers  (2023-06-18T04:34:17Z)
• 3D Data Augmentation for Driving Scenes on Camera [50.41413053812315]
  We propose a 3D data augmentation approach termed Drive-3DAug, aiming at augmenting the driving scenes on camera in the 3D space. We first utilize Neural Radiance Field (NeRF) to reconstruct the 3D models of background and foreground objects. Then, augmented driving scenes can be obtained by placing the 3D objects with adapted location and orientation at the pre-defined valid region of backgrounds.
  arXiv  Detail & Related papers  (2023-03-18T05:51:05Z)
• Exploring the Capabilities and Limits of 3D Monocular Object Detection -- A Study on Simulation and Real World Data [0.0]
  3D object detection based on monocular camera data is key enabler for autonomous driving. Recent deep learning methods show promising results to recover depth information from single images. In this paper, we evaluate the performance of a 3D object detection pipeline which is parameterizable with different depth estimation configurations.
  arXiv  Detail & Related papers  (2020-05-15T09:05:17Z)
• CRAVES: Controlling Robotic Arm with a Vision-based Economic System [96.56564257199474]
  Training a robotic arm to accomplish real-world tasks has been attracting increasing attention in both academia and industry.<n>This work discusses the role of computer vision algorithms in this field.<n>We present an alternative solution, which uses a 3D model to create a large number of synthetic data.
  arXiv  Detail & Related papers  (2018-12-03T13:28:29Z)

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.