Copertina

Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Aguina-Kang, Rio, Blackburn-Matzen, Kevin James, Groueix, Thibault, Kim, Vladimir, Gadelha, Matheus
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects
di: Barda, Amir, et al.
Pubblicazione: (2024)

3D Space as a Scratchpad for Editable Text-to-Image Generation
di: Saha, Oindrila, et al.
Pubblicazione: (2026)

SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation
di: Saha, Oindrila, et al.
Pubblicazione: (2025)

Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
di: Decatur, Dale, et al.
Pubblicazione: (2025)

Residual Primitive Fitting of 3D Shapes with SuperFrusta
di: Ganeshan, Aditya, et al.
Pubblicazione: (2025)

Removing Reflections from RAW Photos
di: Kee, Eric, et al.
Pubblicazione: (2024)

Learning Continuous 3D Words for Text-to-Image Generation
di: Cheng, Ta-Ying, et al.
Pubblicazione: (2024)

MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback
di: Chen, Chen, et al.
Pubblicazione: (2024)

Splat and Replace: 3D Reconstruction with Repetitive Elements
di: Violante, Nicolás, et al.
Pubblicazione: (2025)

Generative Escher Meshes
di: Aigerman, Noam, et al.
Pubblicazione: (2023)

SAMa: Material-aware 3D Selection and Segmentation
di: Fischer, Michael, et al.
Pubblicazione: (2024)

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence
di: Nguyen, Van Nguyen, et al.
Pubblicazione: (2023)

T-3DGS: Removing Transient Objects for 3D Scene Reconstruction
di: Markin, Alexander, et al.
Pubblicazione: (2024)

Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes
di: Jeong, Seunghoon, et al.
Pubblicazione: (2026)

MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation
di: Kim, Hyunwoo, et al.
Pubblicazione: (2024)

Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes
di: Jain, Umangi, et al.
Pubblicazione: (2026)

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
di: Yang, Zesong, et al.
Pubblicazione: (2025)

TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations
di: Sun, Bo, et al.
Pubblicazione: (2024)

Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search
di: Gumin, Maxim, et al.
Pubblicazione: (2025)

MagicClay: Sculpting Meshes With Generative Neural Fields
di: Barda, Amir, et al.
Pubblicazione: (2024)

Seeing Objects in a Cluttered World: Computational Objectness from Motion in Video
di: Poland, Douglas, et al.
Pubblicazione: (2024)

Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases
di: Aguina-Kang, Rio, et al.
Pubblicazione: (2024)

NOPE: Novel Object Pose Estimation from a Single Image
di: Nguyen, Van Nguyen, et al.
Pubblicazione: (2023)

ClutterNav: Gradient-Guided Search for Efficient 3D Clutter Removal with Learned Costmaps
di: Ravie, Navin Sriram, et al.
Pubblicazione: (2025)

Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting
di: Guo, Zijing, et al.
Pubblicazione: (2025)

PoissonNet: A Local-Global Approach for Learning on Surfaces
di: Maesumi, Arman, et al.
Pubblicazione: (2025)

GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes
di: Back, Seunghyeok, et al.
Pubblicazione: (2025)

Imperative vs. Declarative Programming Paradigms for Open-Universe Scene Generation
di: Gumin, Maxim, et al.
Pubblicazione: (2025)

Text-guided Controllable Mesh Refinement for Interactive 3D Modeling
di: Chen, Yun-Chun, et al.
Pubblicazione: (2024)

Generative Cutout Animation
di: Ivan Puhachov, et al.
Pubblicazione: (2026)

Robust Dynamic Object Detection in Cluttered Indoor Scenes via Learned Spatiotemporal Cues
di: Rached, Juan, et al.
Pubblicazione: (2026)

Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality
di: Wang, Beichen, et al.
Pubblicazione: (2026)

GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis
di: Petrov, Dmitry, et al.
Pubblicazione: (2024)

DepthFocus: Controllable Depth Estimation for See-Through Scenes
di: Min, Junhong, et al.
Pubblicazione: (2025)

SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction
di: Jain, Neham, et al.
Pubblicazione: (2025)

Raymoval: Raycasting-based Dynamic Object Removal for Static 3D Mapping
di: Kim, Daebeom, et al.
Pubblicazione: (2026)

ClutterGen: A Cluttered Scene Generator for Robot Learning
di: Jia, Yinsen, et al.
Pubblicazione: (2024)

Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes
di: Noh, Jeongho, et al.
Pubblicazione: (2026)

ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes
di: Chen, Jianqiu, et al.
Pubblicazione: (2023)

Learning Goal-Directed Object Pushing in Cluttered Scenes With Location-Based Attention
di: Dengler, Nils, et al.
Pubblicazione: (2024)