VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds
Not on the map. Why?
Abstract (arXiv)
State-of-the-art 3D reconstruction models, whether from visual, range, or both, tend to underperform on thin objects. This is partially due to the small amount of space such objects occupy in RGB images and in 3D point clouds. To test the extent of their errors, we collected the first thin object dataset comprising of synchronized RGB images, depth maps, and tactile response maps, where each frame is associated with inertial measurements, camera pose and calibration, and groundtruth depth and segmentation maps obtained from laser scanning of thin objects. We hypothesize that tactile data can aid in the reconstruction of thin objects as their response maps provide local shape and deformation information. Our dataset, termed VisTa3D, comprises of 387 scenes covering 70 thin objects over 17 environments. We benchmarked current 3D reconstruction models on VisTa3D and found that, indeed, they exhibit low fidelity on thin objects. To test if tactile data can help, we introduce the first visual-range-tactile 3D reconstruction model as a baseline. Code and data: https://huggingface.co/datasets/shaniaguo/VisTa3D.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 75 of its 107 references that are in the map. First posted on arXiv 21 Aug 2026.
Builds on
75 of 107 references.
References · 75
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021Vision Transformers for Dense Predictioncited by 1,803
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
- 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2024Depth Anything V2cited by 1,422
- 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
38 more
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
- 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
- 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
- 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
- 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
- 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
- 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
- 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
- 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
- 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 207
- 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
- 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
- 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
- 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
- 2024Binding Touch to Everything: Learning Unified Multimodal Tactile Representationscited by 95
- 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 89
- 2022Dynamic Spatial Propagation Network for Depth Completioncited by 71
- 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
- 2024Bilateral Propagation Network for Depth Completioncited by 60
- 2019Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Predictioncited by 44
- 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 40
- 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
- 2019TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereocited by 34
- 2018Geo-Supervised Visual Depth Predictioncited by 33
- 20183D Shape Perception from Monocular Vision, Touch, and Shape Priorscited by 31
- 2021ShapeMap 3-D: Efficient shape mapping through dense touch and visioncited by 31
- 2021An Adaptive Framework for Learning Unsupervised Depth Completioncited by 30
- 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
- 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 30
- 2024Test-Time Adaptation for Depth Completioncited by 26
- 2024Tactile-Augmented Radiance Fieldscited by 26
- 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
- 2019Tactile Mapping and Localization from High-Resolution Tactile Imprintscited by 19
50 most cited of 75 All 75 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.