The paper introduces a new sequential text‑to‑scene generation framework that jointly produces scene layouts and objects. It proposes a 3D Autoregressive Diffusion model (3D‑ARD+) that first generates coarse 3D latents conditioned on text and the current scene, then refines them into fine‑grained object geometry and appearance. A large dataset of 230K indoor scenes with paired text instructions is curated for training, and the model demonstrates the ability to place objects according to complex spatial and semantic text prompts.
arXiv:2502. 06819v2 Announce Type: replace Abstract: This paper presents a framework for generating 3D indoor scenes from text prompts.
WorldSculpt presents a method for generating compositional 3D representations of cluttered scenes with hundreds of objects by adapting a single-object 3D generative prior to multi-view observations. The approach, built on Pixal3D with a multi-view conditioning pathway, can generalize to highly occluded scenes without scene-level training. The authors also introduce the UE-MeshyScene benchmark and demonstrate that their method outperforms prior approaches across various evaluation settings, including converting existing 3DGS worlds into compositional mesh scenes.
arXiv:2606. 24206v1 Announce Type: cross Abstract: Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model.
arXiv:2607. 02407v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments.
arXiv:2601.14056v2 Announce Type: replace-cross Abstract: Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance d...
arXiv:2603.22782v3 Announce Type: replace Abstract: Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity...
The paper introduces Chat-Edit-3D++ (CE3D++), an interactive 3D and 4D scene editing system that uses a Hash-Atlas network to separate 2D editing from 3D reconstruction. CE3D++ employs a large language model to accept arbitrary textual input, interpret user intent, and autonomously invoke appropriate visual models, enabling multi‑round dialogue and diverse editing effects. The approach is extended to monocular 4D scenes by adding motion constraints and a trajectory dataset, allowing a smaller LLM to schedule up to 30 visual tools accurately.
SpaceFlow is a training‑free pipeline that enables locally controllable 3D generation from text and geometric primitives. Each primitive acts as a proxy for an object part and receives a local control level, allowing users to dictate strict adherence to input shapes or permit generative completion in different regions. The method enforces spatial constraints during structure generation and matches appearance to primitives, limiting cross‑part leakage and achieving state‑of‑the‑art prompt faithfulness and material accuracy.
The paper introduces T23D-CompBench, a new benchmark for fine‑grained text‑to‑3D quality assessment that includes 3,600 textured meshes generated from ten state‑of‑the‑art models and 129,600 human ratings. It also proposes Rank2Score, a two‑stage rank‑learning metric that first trains with supervised contrastive regression and curriculum learning, then refines predictions using mean opinion scores to better align with human judgments. Experiments show Rank2Score outperforms existing metrics and can be used as a reward function for generative model optimization.
arXiv:2609.22916v1 Announce Type: new Abstract: Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit la...
ScenePilot introduces a retrieval‑augmented Grow‑and‑Repair framework for text‑driven 3D indoor scene generation. It uses a Hierarchical Retrieval‑Augmented Planning module to fetch room, group, and anchor layout priors, then incrementally inserts object groups with a base generator, while a Reinforcement Multimodal Repair module performs lightweight local corrections after each insertion and a final global repair. The approach is trained on a new SceneReverse‑17k dataset of perturbed scenes, enabling the policy to predict structured move‑rotate‑scale actions from rendered views, scene state, retrieved priors, and edit history, thereby improving physical plausibility, functional coherence, and controllability without heavy full‑scene optimization.
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. It learns a compact voxel‑aligned latent space using photometric supervision via differentiable 3D Gaussian Splatting, and employs a masked autoregressive transformer to predict missing voxel occupancy and latent tokens. Experiments on synthetic indoor scenes and RealEstate10k show that SPAR3S achieves higher novel‑view quality than prior methods and generalizes to real‑world data.