TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Unconstrained Scene Generation with Locally Conditioned Ra...

Unconstrained Scene Generation with Locally Conditioned Radiance Fields

Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind

2021-04-01ICCV 2021 10Scene Generation
PaperPDFCode(official)

Abstract

We tackle the challenge of learning a distribution over complex, realistic, indoor scenes. In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera. Our model can be used as a prior to generate new scenes, or to complete a scene given only sparse 2D observations. Recent work has shown that generative models of radiance fields can capture properties such as multi-view consistency and view-dependent lighting. However, these models are specialized for constrained viewing of single objects, such as cars or faces. Due to the size and complexity of realistic indoor environments, existing models lack the representational capacity to adequately capture them. Our decomposition scheme scales to larger and more complex scenes while preserving details and diversity, and the learned prior enables high-quality rendering from viewpoints that are significantly different from observed viewpoints. When compared to existing models, GSN produces quantitatively higher-quality scene renderings across several different scene datasets.

Results

TaskDatasetMetricValueModel
Image GenerationVizDoomFID37.21GSN
Image GenerationVizDoomFID (SwAV)4.56GSN
Image GenerationReplicaFID41.75GSN
Image GenerationReplicaFID (SwAV)4.14GSN
Scene GenerationReplicaFID41.75GSN
Scene GenerationReplicaSwAV-FID4.14GSN
Scene GenerationAVDFID51.11GSN
Scene GenerationAVDSwAV-FID6.59GSN
Scene GenerationVizDoomFID37.21GSN
Scene GenerationVizDoomSwAV-FID4.56GSN
16kReplicaFID41.75GSN
16kReplicaSwAV-FID4.14GSN
16kAVDFID51.11GSN
16kAVDSwAV-FID6.59GSN
16kVizDoomFID37.21GSN
16kVizDoomSwAV-FID4.56GSN

Related Papers

World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving2025-07-17$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting2025-07-12Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures2025-07-07Voyaging into Unbounded Dynamic Scenes from a Single View2025-07-05XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation2025-06-26From 2D to 3D Cognition: A Brief Survey of General World Models2025-06-25WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration2025-06-25DreamAnywhere: Object-Centric Panoramic 3D Scene Generation2025-06-25