DRAWER: Digital Reconstruction and Articulation With Environment Realism
Hongchi Xia, Entong Su, Marius Memmel, Arhan Jain, Raymond Yu, Numfor Mbiziwo-Tiapo, Ali Farhadi, Abhishek Gupta, Shenlong Wang, Wei-Chiu Ma
2025年份
12顶会引用
摘要
Figure 1. DRAWER automatically converts a video of a static scene into an interactive environment with segmented objects and articulated doors. It supports physical interactions like opening/closing drawers and moving/placing objects, with precise geometry and high-fidelity rendering. With these capabilities, DRAWER can transform a video into interactive games and enable real-to-sim-to-real transfer in robotics.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper12
- PointWorld: Scaling 3D World Models for In-The-Wild Robotic ManipulationWenlong Huang, Yu-Wei Chao, Arsalan Mousavian, Ming-Yu Liu 等CVPR 2026 · 被引用 87 次
- SAGE: Scalable Agentic 3D Scene Generation for Embodied AIHongchi Xia, Xuan Li, Zhaoshuo Li, Qianli Ma 等CVPR 2026 · 被引用 50 次
- HoloScene: Simulation-Ready Interactive 3D Worlds from a Single VideoHongchi Xia, Chih-Hao Lin, Hao-Yu Hsu, Quentin Leboutet 等NeurIPS 2025 · 被引用 18 次
- Dexterous World ModelsByungjun Kim, Taeksoo Kim, Junyoung Lee, Hanbyul JooCVPR 2026 · 被引用 17 次
- VoMP: Predicting Volumetric Mechanical Property FieldsRishit Dagli, Donglai Xiang, Vismay Modi, Charles Loop 等ICLR 2026 · 被引用 13 次
它引用的顶会 Paper49
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 等ICCV 2021 · 被引用 2,700 次
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt 等NeurIPS 2021 · 被引用 2,500 次
相关 Paper
- Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single VideoHongchi Xia, Zhi-Hao Lin, Wei-Chiu Ma, Shenlong WangCVPR 2024 · 被引用 9 次
- DecoupledGaussian: Object-Scene Decoupling for Physics-Based InteractionMiaowei Wang, Yibo Zhang, Weiwei Xu, Rui Ma 等CVPR 2025
- LeviTor: 3D Trajectory Oriented Image-to-Video SynthesisHanlin Wang, Hao Ouyang, Qiuyu Wang, Wen Wang 等CVPR 2025
- SketchVideo: Sketch-based Video Generation and EditingFeng-Lin Liu, Hongbo Fu, Xintao Wang, Weicai Ye 等CVPR 2025
- ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction GenerationLing-An Zeng, Guohong Huang, Yi-Lin Wei, Shengbo Gu 等CVPR 2025
