Research map / Detection and segmentation / Open-set and few-shot detection
ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace ObjectFolder 1.0 with ObjectFolder 2.0 rendering | ObjectFolder · Vision rendering | Rendering time: 3.699 -> 0.062 seconds | Helped |
| Replace ObjectFolder 1.0 with ObjectFolder 2.0 rendering | ObjectFolder · Audio rendering | Rendering time: 0.420 -> 0.035 seconds | Helped |
| Replace ObjectFolder 1.0 with ObjectFolder 2.0 rendering | ObjectFolder · Touch rendering | Rendering time: 0.010 -> 0.014 seconds | Hurt |
| Use ObjectFolder 2.0 multisensory rendering pipeline | ObjectFolder · Multisensory rendering | Total rendering time: 4.129 -> 0.111 seconds | Helped |
| Use ObjectFolder 2.0 visual representation | ObjectFolder · Multisensory rendering | Vision PSNR: 35.7 -> 36.3 | Helped |
| Use ObjectFolder 2.0 visual representation | ObjectFolder · Multisensory rendering | Vision SSIM: 0.97 -> 0.98 | Helped |
| Predict location-dependent modal gains and synthesize the remaining audio signal | AudioNet · Multisensory rendering | Audio STFT Distance: 4.94 -> 0.19 | Helped |
| Use ObjectFolder 2.0 tactile simulation and representation | ObjectFolder · Multisensory rendering | Touch PSNR: 27.9 -> 31.6 | Helped |
| Train on ObjectFolder 2.0 rather than ObjectFolder 1.0 visual data | Object scale estimation · Real objects | Mean scale error: 7.41 -> 5.08 cm | Helped |
| Train on ObjectFolder 2.0 rather than ObjectFolder 1.0 audio data | Object scale estimation · Real objects | Mean scale error: 6.85 -> 4.68 cm | Helped |
| Train on ObjectFolder 2.0 rather than ObjectFolder 1.0 tactile data | Object scale estimation · Real objects | Mean scale error: 4.92 -> 3.51 cm | Helped |
| Combine tactile readings with impact sounds | Contact localization · Audio-tactile contact localization | Mean distance to ground-truth contact | Helped |
Closest papers by meaning
- MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World (CVPR 2024 · similarity 0.86)
- EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI (CVPR 2024 · similarity 0.85)
- EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? (NeurIPS 2025 · similarity 0.85)
- A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning (CVPR 2025 · similarity 0.85)
- MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes (CVPR 2025 · similarity 0.85)
- DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$ (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.