Cover Image

Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Che, Henry, Wang, Jingkang, Chen, Yun, Yang, Ze, Manivasagam, Sivabalan, Urtasun, Raquel
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

G3R: Gradient Guided Generalizable Reconstruction
by: Chen, Yun, et al.
Published: (2024)

Flux4D: Flow-based Unsupervised 4D Reconstruction
by: Wang, Jingkang, et al.
Published: (2025)

GenAssets: Generating in-the-wild 3D Assets in Latent Space
by: Yang, Ze, et al.
Published: (2026)

SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time
by: Chen, Yun, et al.
Published: (2025)

UniCal: Unified Neural Sensor Calibration
by: Yang, Ze, et al.
Published: (2024)

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
by: Zhang, Lunjun, et al.
Published: (2023)

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes
by: Chen, Xiao, et al.
Published: (2025)

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
by: Chen, Xiao, et al.
Published: (2024)

UnO: Unsupervised Occupancy Fields for Perception and Forecasting
by: Agro, Ben, et al.
Published: (2024)

GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstruction
by: Zhang, Hanyue, et al.
Published: (2024)

QuAD: Query-based Interpretable Neural Motion Planning for Autonomous Driving
by: Biswas, Sourav, et al.
Published: (2024)

Towards Realistic Scene Generation with LiDAR Diffusion Models
by: Ran, Haoxi, et al.
Published: (2024)

Genie 4D: Semantic-Prior-Guided 4D Dynamic Scene Reconstruction
by: Yang, Yiru, et al.
Published: (2026)

MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
by: Che, Lirong, et al.
Published: (2026)

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent
by: Yu, Che Rin, et al.
Published: (2025)

DeTra: A Unified Model for Object Detection and Trajectory Forecasting
by: Casas, Sergio, et al.
Published: (2024)

UrbanVLA: A Vision-Language-Action Model for Urban Micromobility
by: Li, Anqi, et al.
Published: (2025)

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
by: Li, Haoyuan, et al.
Published: (2025)

SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation
by: Zhang, Jiwen, et al.
Published: (2026)

Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement
by: Feng, Zhicheng, et al.
Published: (2025)

Human-like Navigation in a World Built for Humans
by: Chandaka, Bhargav, et al.
Published: (2025)

Planning with the Views via Scene Self-Exploration
by: Wang, Kangrui, et al.
Published: (2026)

Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes
by: Chen, Siang, et al.
Published: (2024)

nuCarla: A nuScenes-Style Bird's-Eye View Perception Dataset for CARLA Simulation
by: Qiao, Zhijie, et al.
Published: (2025)

DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy
by: Wang, Yuran, et al.
Published: (2025)

Efficient Diffusion as Low Light Enhancer
by: Lan, Guanzhou, et al.
Published: (2024)

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
by: Chen, Yandu, et al.
Published: (2025)

Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
by: Chen, Shizhe, et al.
Published: (2025)

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
by: Wu, Wayne, et al.
Published: (2024)

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
by: Shen, Yichao, et al.
Published: (2025)

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
by: Zadaianchuk, Andrii, et al.
Published: (2026)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
by: Ni, Chaojun, et al.
Published: (2024)

Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
by: Yuan, Zhecheng, et al.
Published: (2024)

SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
by: Wu, Tianshu, et al.
Published: (2026)

Memorize What Matters: Emergent Scene Decomposition from Multitraverse
by: Li, Yiming, et al.
Published: (2024)

SPGrasp: Spatiotemporal Prompt-driven Grasp Synthesis in Dynamic Scenes
by: Mei, Yunpeng, et al.
Published: (2025)

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
by: Feng, ZhiYuan, et al.
Published: (2026)

Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling
by: Yu, Xihang, et al.
Published: (2026)

g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
by: Wang, Zihan, et al.
Published: (2024)

CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
by: Gan, Rui, et al.
Published: (2026)