Scene Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

9 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 122 papers with code (309 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Funnel Activation for Visual Recognition
  23 Jul 2020 7 repositories listed
  We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial…
• LUMINOUS: Indoor Scene Generation for Embodied AI Challenges
  10 Nov 2021 4 repositories listed
  However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts.
• ROOT: VLM based System for Indoor Scene Understanding and Beyond
  24 Nov 2024 3 repositories listed
  To train our SceneVLM, we collect over 610, 000 images from various public indoor datasets and implement a scene data generation pipeline with a semi-automated technique to establish relationships and estimate distances…
• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
  2 Dec 2020 3 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 2 pointer-only (licence)
  We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering.
• GPD-1: Generative Pre-training for Driving
  11 Dec 2024 2 repositories listed
  We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem.
• LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
  11 Dec 2024 2 repositories listed Syntology ran 6 of 23 samples · 17 unverified · 12 pointer-only (licence)
  However, existing T2I models show decayed performance in compositional image generation involving multiple objects and intricate relationships.
• Alfie: Democratising RGBA Image Generation With No $$$
  27 Aug 2024 2 repositories listed
  Designs and artworks are ubiquitous across various creative fields, requiring graphic design skills and dedicated software to create compositions that include many graphical elements, such as logos, icons, symbols, and…
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents
  8 Aug 2024 2 repositories listed Syntology ran 6 of 11 samples · 5 unverified
  The emergence of foundation models as the "brain" of EAI agents for high-level task planning has shown promising results.
• Pyramid Diffusion for Fine 3D Large Scene Generation
  20 Nov 2023 2 repositories listed Syntology ran 11 of 12 samples · 1 unverified
  We introduce a framework, the Pyramid Discrete Diffusion model (PDD), which employs scale-varied diffusion models to progressively generate high-quality outdoor scenes.
• GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
  20 Apr 2021 2 repositories listed
  Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori…
• Generative Adversarial Transformers
  1 Mar 2021 2 repositories listed Syntology ran 5 of 6 samples · 1 unverified
  We introduce the GANformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling.
• SceneFormer: Indoor Scene Generation with Transformers
  17 Dec 2020 2 repositories listed
  In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers.
• Learning Object Placements For Relational Instructions by Hallucinating Scene Representations
  23 Jan 2020 2 repositories listed
  One particular requirement for such robots is that they are able to understand spatial relations and can place objects in accordance with the spatial relations expressed by their user.
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
  27 Dec 2019 2 repositories listed
  To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately…
• Learning Canonical Representations for Scene Graph to Image Generation
  16 Dec 2019 2 repositories listed Syntology ran 2 of 17 samples · 15 unverified
  Generating realistic images of complex visual scenes becomes challenging when one wishes to control the structure of the generated images.
• Semantic Bottleneck Scene Generation
  26 Nov 2019 2 repositories listed
  For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts.
• Specifying Object Attributes and Relations in Interactive Scene Generation
  11 Sep 2019 2 repositories listed Syntology ran 0 of 16 samples · 16 unverified
  We introduce a method for the generation of images from an input scene graph.
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
  30 Jul 2019 2 repositories listed
  Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning.
• SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
  25 Jul 2019 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.
• LayoutVAE: Stochastic Scene Layout Generation From a Label Set
  24 Jul 2019 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  Recently there is an increasing interest in scene generation within the research community.
• Scenic: A Language for Scenario Specification and Scene Generation
  25 Sep 2018 2 repositories listed
  We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning.
• I²-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
  12 Jul 2025 1 repository listed
  Forecasting the evolution of 3D scenes and generating unseen scenarios via occupancy-based world models offers substantial potential for addressing corner cases in autonomous driving systems.
• XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
  26 Jun 2025 1 repository listed Syntology ran 0 of 10 samples · 10 unverified
  Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of…
• Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
  20 Jun 2025 1 repository listed Syntology ran 0 of 9 samples · 9 unverified
  Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene.
• 3D Scene Generation: A Survey
  8 May 2025 1 repository listed
  Recent advances in deep generative models (e.
• Steerable Scene Generation with Post Training and Inference-Time Search
  7 May 2025 1 repository listed
  We introduce a novel MCTS-based inference-time search strategy for diffusion models, enforce feasibility via projection and simulation, and release a dataset of over 44 million SE(3) scenes spanning five diverse…
• DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion
  3 May 2025 1 repository listed
  However, existing approaches, which primarily use 3D bounding boxes and binary maps for foreground and background control, fall short in capturing the complexity of the scene and integrating multi-modal information.
• HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
  30 Apr 2025 1 repository listed Syntology ran 2 of 8 samples · 6 unverified
  To address this issue, we propose HoloTime, a framework that integrates video diffusion models to generate panoramic videos from a single prompt or reference image, along with a 360-degree 4D scene reconstruction method…
• EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations
  7 Apr 2025 1 repository listed
  We benchmark EP-Diffuser against two SotA models in terms of accuracy and plausibility of predictions on the Argoverse 2 dataset.
• Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
  26 Mar 2025 1 repository listed
  We present Free4D, a novel tuning-free framework for 4D scene generation from a single image.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.