AI Paper Atlas

Research map / 3D vision / 3D generation

TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation

Ziqian Wang, Yonghao He, Licheng Yang, Wei Zou, Hongxuan Ma, Liu.Liu Liu.Liu, Wei Sui, Yuxin Guo, Hu Su

ECCV 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
add Differentiable Rotation Optimizer (vs MLLM-only rotation) (ablation)TabletopGen · Image-to-sceneCol_S (%): 16.67 -> 7.69Improved
add DRO (ablation)TabletopGen · Image-to-sceneDINOv2: 0.8261 -> 0.8383Improved
add Top-View Spatial Alignment (vs MLLM-only translation and scale) (ablation)TabletopGen · Image-to-sceneCol_S (%): 61.54 -> 7.69Improved
add TSA (ablation)TabletopGen · Image-to-sceneLPIPS: 0.4799 -> 0.4483Improved
remove both DRO and TSA vs removing TSA only (ablation)TabletopGen · Image-to-sceneCol_S (%): 61.54 -> 62.82No clear effect
TabletopGen vs best image-driven baseline MIDIMIDI · Image-to-sceneCol_S (%): 98.72 -> 7.69Improved
TabletopGen vs MIDIMIDI · Image-to-sceneGPT-4o average: 4.33 -> 6.19Improved
TabletopGen vs MesaTask on text-to-sceneMesaTask · Text-to-sceneGPT-4o average: 4.12 -> 6.27Improved
TabletopGen vs Holodeck-table collisionsHolodeck-table · Text-to-sceneCol_S (%): 0.00 -> 6.67Hurt
TabletopGen vs MIDI under mean-view protocolMIDI · Image-to-sceneDINOv2 gain: +0.1313 -> +0.1473Improved
TabletopGen vs MIDI in user studyMIDI · User studyoverall preference (%): 11.61 -> 83.13Improved
TabletopGen vs SceneGen/FlashSculptor on stabilityFlashSculptor · Image-to-sceneDSS (%): 6.42 -> 92.13Improved

Later papers that compared with this method

2 later accepted papers report TabletopGen as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy