No article text was recorded for this version.
modular scene decomposition
Version 1 of 1108 papers129 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compressible-composable NeRF via Rank-residual Decomposition
- Blog: STaR: Self-Supervised Tracking and Reconstruction of Rigid Objects in Motion With Neural Rendering
- Blog: Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes
- Blog: ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
- Blog: Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation
- Blog: DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis
- Blog: CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout
- Blog: Disentangled 3D Scene Generation with Layout Learning
- Blog: CityDreamer: Compositional Generative Model of Unbounded 3D Cities
- Blog: OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
- Blog: Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream
- Blog: Dynamic LiDAR Re-simulation using Compositional Neural Fields
- Blog: GO-NeRF: Generating Virtual Objects in Neural Radiance Fields
- Blog: NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects
- Blog: Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation
- Blog: Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models
- Blog: Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation
- Blog: Unsupervised 3D Scene Representation Learning via Movable Object Inference
- Blog: Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision
- Blog: Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture
- Blog: CityDreamer: Compositional Generative Model of Unbounded 3D Cities
- Blog: AutoRecon: Automated 3D Object Discovery and Reconstruction
- Blog: Neural Lighting Simulation for Urban Scenes
- Blog: Scalable 3D Object-centric Learning
- Blog: Learning Compact Representations for LiDAR Completion and Generation
- Blog: DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
- Blog: Neural Radiance Field in Autonomous Driving: A Survey
- Blog: Embedded Representation Learning Network for Animating Styled Video Portrait
- Blog: Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields
- Blog: Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
- Blog: CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
- Blog: Structured-NeRF: Hierarchical Scene Graph with Neural Representation
- Blog: Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering
- Blog: AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
- Blog: Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts
- Blog: Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
- Blog: Looking Into the Water by Unsupervised Learning of the Surface Shape
- Blog: 3D Data Augmentation for Driving Scenes on Camera
- Blog: The Radiance of Neural Fields: Democratizing Photorealistic and Dynamic Robotic Simulation
- Blog: UniSim: A Neural Closed-Loop Sensor Simulator
- Blog: In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
- Blog: Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
- Blog: Learning Multi-Object Dynamics with Compositional Neural Radiance Fields
- Blog: Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes
- Blog: DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
- Blog: ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary
- Blog: AutoRecon: Automated 3D Object Discovery and Reconstruction
- Blog: Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views
- Blog: Semantic 3D-Aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field
- Blog: DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
- Blog: Variational Inference for Scalable 3D Object-centric Learning
- Blog: NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
- Blog: Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
- Blog: Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
- Blog: Object-Centric Neural Scene Rendering
- Blog: Single-Shot Scene Reconstruction
- Blog: Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
- Blog: Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
- Blog: Representing 3D Shapes with Probabilistic Directed Distance Fields
- Blog: Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation
Showing 60 of 108 papers.
History & citation
Current · Permanent link
- This direction split from Decomposing 3D Scenes into Editable Semantic Parts (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_modular_scene_decomposition_2fed73ba,
title = {modular scene decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/modular-scene-decomposition/rdr_2fed73ba516b4addb7ebec015d80511f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_modular_scene_decomposition_2fed73ba_v1,
title = {modular scene decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/modular-scene-decomposition/rdr_2fed73ba516b4addb7ebec015d80511f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}