paper-with-me

홈 › Papers

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

2025-06-03 · CVPR 2025 1 · Tongyuan Bai, Wangyuanfan Bai, Dong Chen, Tieru Wu, Manyi Li, Rui Ma

Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based control, which offers better controllability but demands considerable knowledge for the cumbersome graph design process. To address these challenges, we present FreeScene, a user-friendly framework that enables both convenient and effective control for indoor scene synthesis.Specifically, FreeScene supports free-form user inputs including text description and/or reference images, allowing users to express versatile design intentions. The user inputs are adequately analyzed and integrated into a graph representation by a VLM-based Graph Designer. We then propose MG-DiT, a Mixed Graph Diffusion Transformer, which performs graph-aware denoising to enhance scene generation. Our MG-DiT not only excels at preserving graph structure but also offers broad applicability to various tasks, including, but not limited to, text-to-scene, graph-to-scene, and rearrangement, all within a single model. Extensive experiments demonstrate that FreeScene provides an efficient and user-friendly solution that unifies text-based and graph based scene synthesis, outperforming state-of-the-art methods in terms of both generation quality and controllability in a range of applications.

📄 PDF Abstract BibTeX arXiv:2506.02781

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingIndoor Scene SynthesisScene Generation

Methods 이 논문이 사용한 방법론

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

Mixed Diffusion for 3D Indoor Scene Synthesis

2024-05-31 · Siyi Hu, Diego Martin Arroyo, Stephanie Debats, Fabian Manhardt 외

Generating realistic 3D scenes is an area of growing interest in computer vision and robotics. However, creating high-quality, diverse synthetic 3D content often requires expert intervention, making it costly and complex…

DenoisingIndoor Scene Synthesis

Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion

2023-09-21 · NeurIPS 2023 11

In this work, we investigate the task of text-to-image (T2I) synthesis under the abstract-to-intricate setting, i.e., generating intricate visual content from simple abstract text prompts. Inspired by human imagination i…

Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis

2022-08-29 · Wan-Cyuan Fan, Yen-Chun Chen, Dongdong Chen, Yu Cheng 외

Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details…

Conditional Image GenerationDenoisingImage GenerationRepresentation Learning

3D Scene Diffusion Guidance using Scene Graphs

2023-08-08 · Mohammad Naanaa, Katharina Schmid, Yinyu Nie

Guided synthesis of high-quality 3D scenes is a challenging task. Diffusion models have shown promise in generating diverse data, including 3D scenes. However, current methods rely directly on text embeddings for control…

Denoising

SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion

2025-02-11 · Yannik Frisch, Ssharvien Kumar Sivakumar, Çağhan Köksal, Elsa Böhm 외

Surgical simulation offers a promising addition to conventional surgical training. However, available simulation tools lack photorealism and rely on hardcoded behaviour. Denoising Diffusion Models are a promising alterna…

DenoisingImage Generation