Copertina

SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Asim, Mohammad, Wewer, Christopher, Lenssen, Jan Eric
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MEt3R: Measuring Multi-View Consistency in Generated Images
di: Asim, Mohammad, et al.
Pubblicazione: (2025)

MixFlow: Mixed Source Distributions Improve Rectified Flows
di: Nayal, Nazir, et al.
Pubblicazione: (2026)

Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priors
di: Paul, Soumava, et al.
Pubblicazione: (2024)

Spatial Reasoners for Continuous Variables in Any Domain
di: Pogodzinski, Bart, et al.
Pubblicazione: (2025)

Spatial Reasoning with Denoising Models
di: Wewer, Christopher, et al.
Pubblicazione: (2025)

Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion
di: Mou, Linzhan, et al.
Pubblicazione: (2024)

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
di: Ke, Tsung-Wei, et al.
Pubblicazione: (2024)

EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion
di: Zhai, Guangyao, et al.
Pubblicazione: (2024)

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing
di: Chen, Jun-Kun, et al.
Pubblicazione: (2024)

SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis
di: Chen, Xinya, et al.
Pubblicazione: (2026)

Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
di: Wu, Ziyi, et al.
Pubblicazione: (2024)

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI
di: Yang, Yandan, et al.
Pubblicazione: (2024)

Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models
di: Burgess, James, et al.
Pubblicazione: (2023)

SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
di: Hu, Ziniu, et al.
Pubblicazione: (2024)

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation
di: Hou, Xiaolu, et al.
Pubblicazione: (2025)

DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
di: Zhuo, Dong, et al.
Pubblicazione: (2026)

ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF
di: Park, Jangho, et al.
Pubblicazione: (2023)

Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
di: Galesso, Silvio, et al.
Pubblicazione: (2024)

VidTok: A Versatile and Open-Source Video Tokenizer
di: Tang, Anni, et al.
Pubblicazione: (2024)

RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion
di: Shriram, Jaidev, et al.
Pubblicazione: (2024)

DORSal: Diffusion for Object-centric Representations of Scenes et al
di: Jabri, Allan, et al.
Pubblicazione: (2023)

Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding
di: He, Ziyao, et al.
Pubblicazione: (2026)

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection
di: Zeng, Shuai, et al.
Pubblicazione: (2024)

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
di: Yang, Cheng-Kun, et al.
Pubblicazione: (2023)

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
di: Jia, Baoxiong, et al.
Pubblicazione: (2024)

Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification
di: Barros, Artur, et al.
Pubblicazione: (2025)

OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
di: Engelmann, Francis, et al.
Pubblicazione: (2024)

SceneFoundry: Generating Interactive Infinite 3D Worlds
di: Chen, ChunTeng, et al.
Pubblicazione: (2026)

D$^3$epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes
di: Chen, Siyu, et al.
Pubblicazione: (2024)

MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation
di: Yang, Zhifei, et al.
Pubblicazione: (2025)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
di: Gao, Ziqi, et al.
Pubblicazione: (2024)

Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
di: Schröppel, Philipp, et al.
Pubblicazione: (2023)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
di: You, Haoran, et al.
Pubblicazione: (2024)

Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding
di: Bhanushali, Jay, et al.
Pubblicazione: (2022)

GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
di: Chou, Zi-Ting, et al.
Pubblicazione: (2024)

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
di: Wu, Yuqi, et al.
Pubblicazione: (2024)

6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction
di: Gieruc, Théo, et al.
Pubblicazione: (2024)

TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding
di: Nguyen, Duc, et al.
Pubblicazione: (2025)

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
di: Tang, Lv, et al.
Pubblicazione: (2026)

RoboLayout: Differentiable 3D Scene Generation for Embodied Agents
di: Shamsaddinlou, Ali
Pubblicazione: (2026)