TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation

• URL: http://arxiv.org/abs/2502.07840v1
• Date: Tue, 11 Feb 2025 03:43:56 GMT
• Title: TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
• Authors: Jeongyun Kim, Jeongho Noh, Dong-Guw Lee, Ayoung Kim,
• Abstract summary: TranSplat is a surface embedding-guided 3D Gaussian Splatting method tailored for transparent objects. By integrating these surface embeddings with input RGB images, TranSplat effectively captures the complexities of transparent surfaces.
• Score: 10.957451368533302
• License:
• Abstract: Transparent object manipulation remains a sig- nificant challenge in robotics due to the difficulty of acquiring accurate and dense depth measurements. Conventional depth sensors often fail with transparent objects, resulting in in- complete or erroneous depth data. Existing depth completion methods struggle with interframe consistency and incorrectly model transparent objects as Lambertian surfaces, leading to poor depth reconstruction. To address these challenges, we propose TranSplat, a surface embedding-guided 3D Gaussian Splatting method tailored for transparent objects. TranSplat uses a latent diffusion model to generate surface embeddings that provide consistent and continuous representations, making it robust to changes in viewpoint and lighting. By integrating these surface embeddings with input RGB images, TranSplat effectively captures the complexities of transparent surfaces, enhancing the splatting of 3D Gaussians and improving depth completion. Evaluations on synthetic and real-world transpar- ent object benchmarks, as well as robot grasping tasks, show that TranSplat achieves accurate and dense depth completion, demonstrating its effectiveness in practical applications. We open-source synthetic dataset and model: https://github. com/jeongyun0609/TranSplat

Related papers

• TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network [8.487135422430972]
  We propose TDCNet, a novel dual-branch CNN-Transformer parallel network for transparent object depth completion. Our model achieves state-of-the-art performance across multiple public datasets.
  arXiv  Detail & Related papers  (2024-12-19T15:42:21Z)
• G2SDF: Surface Reconstruction from Explicit Gaussians with Implicit SDFs [84.07233691641193]
  We introduce G2SDF, a novel approach that integrates a neural implicit Signed Distance Field into the Gaussian Splatting framework. G2SDF achieves superior quality than prior works while maintaining the efficiency of 3DGS.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• 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. Our method incorporates a parameter-aligned, domain-adaptive, and physically realistic Sim2Real simulation for efficient data generation. Our experimental results demonstrate the model's exceptional Sim2Real generalizability in real-world scenarios.
  arXiv  Detail & Related papers  (2024-09-13T15:44:38Z)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• Hybrid Explicit Representation for Ultra-Realistic Head Avatars [55.829497543262214]
  We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time. UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures. Experiments that our modeled results exceed those of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-03-18T04:01:26Z)
• RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation [50.10282876199739]
  This paper introduces RFTrans, an RGB-D-based method for surface normal estimation and manipulation of transparent objects. It integrates the RFNet, which predicts refractive flow, object mask, and boundaries, followed by the F2Net, which estimates surface normal from the refractive flow. A real-world robot grasping task witnesses an 83% success rate, proving that refractive flow can help enable direct sim-to-real transfer.
  arXiv  Detail & Related papers  (2023-11-21T07:19:47Z)
• TODE-Trans: Transparent Object Depth Estimation with Transformer [16.928131778902564]
  We present a transformer-based transparent object depth estimation approach from a single RGB-D input. To better enhance the fine-grained features, a feature fusion module (FFM) is designed to assist coherent prediction.
  arXiv  Detail & Related papers  (2022-09-18T03:04:01Z)
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction [91.43066633305662]
  We propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD) Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time.
  arXiv  Detail & Related papers  (2022-03-09T17:20:18Z)
• RGB-D Local Implicit Function for Depth Completion of Transparent Objects [43.238923881620494]
  Majority of perception methods in robotics require depth information provided by RGB-D cameras. Standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. We present a novel framework that can complete missing depth given noisy RGB-D input.
  arXiv  Detail & Related papers  (2021-04-01T17:00:04Z)
• 3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning [54.24887282693925]
  We propose a novel framework to exploit 3D dense (depth and surface normals) information for expression manipulation. We use an off-the-shelf state-of-the-art 3D reconstruction model to estimate the depth and create a large-scale RGB-Depth dataset. Our experiments demonstrate that the proposed method outperforms the competitive baseline and existing arts by a large margin.
  arXiv  Detail & Related papers  (2020-09-30T17:12:35Z)

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.