# Tetris3D: 3D Scene Generation With Objects That Fit Together

arXiv: https://arxiv.org/abs/2610.10539 · HTML: https://mlsanity.com/paper/2610.10539/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 66 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Automated Creation of Digital Cousins for Robust Policy Learning](https://mlsanity.com/paper/2410.07408/) (2024)
- [ShapeR: Robust Conditional 3D Shape Generation from Casual Captures](https://mlsanity.com/paper/2601.11514/) (2026)
- [GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence](https://mlsanity.com/paper/2511.21945/) (2025)
- [SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2606.03994/) (2026)
- [Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling](https://mlsanity.com/paper/2602.08058/) (2026)
- [PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction](https://mlsanity.com/paper/2603.05888/) (2026)
- [φ-Scene: Physically Grounded Image-to-3D Scene Reconstruction](https://mlsanity.com/paper/2606.21596/) (2026)
- [Axolotl3D: a Unified Framework for Faithful 3D Shape Completion](https://mlsanity.com/paper/2607.20660/) (2026)
- [SPREAD: Spatial-Physical REasoning via geometry Aware Diffusion](https://mlsanity.com/paper/2603.27573/) (2026)
- [WorldSculpt: Generating Compositional Worlds from Grounded Videos](https://mlsanity.com/paper/2609.05416/) (2026)
- [MessyKitchens: Contact-rich object-level 3D scene reconstruction](https://mlsanity.com/paper/2603.16868/) (2026)
- [Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion](https://mlsanity.com/paper/2604.16552/) (2026)
- [Pose-Aware Diffusion for 3D Generation](https://mlsanity.com/paper/2605.00345/) (2026)
- [PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation](https://mlsanity.com/paper/2606.01649/) (2026)
- [TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation](https://mlsanity.com/paper/2607.21017/) (2026)

## Abstract (arXiv)

We propose Tetris3D, a generative framework for single-image 3D scene reconstruction that recovers objects which are physically and geometrically coherent as a scene. Existing methods often generate objects independently or couple them implicitly, providing limited guidance for ensuring fine-grained spatial compatibility between neighboring objects that interact with one another. To address this, we explicitly condition the generation of each object on the geometry of surrounding objects and their physical relationships, guiding its shape and pose to remain geometrically and physically plausible within the scene. Moreover, we introduce ComOb, a physics simulation-based dataset of 1.2M scenes featuring physical interactions across diverse object categories, with per-object meshes and pairwise physical relation annotations. Comprehensive experiments on synthetic and realworld scenes show that Tetris3D recovers coherent object shapes and poses even when interacting regions are occluded, and achieves state-of-the-art performance in both generation quality and physical stability.