Copertina

Self-Improving 4D Perception via Self-Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Nan, Yu, Pengcheng, Zeng, Weijia, Rehg, James M., Kanazawa, Angjoo, Feng, Haiwen, Wang, Qianqian
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

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
di: Feng, Haiwen, et al.
Pubblicazione: (2025)

Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding
di: Wu, Mingxuan, et al.
Pubblicazione: (2025)

Shape of Motion: 4D Reconstruction from a Single Video
di: Wang, Qianqian, et al.
Pubblicazione: (2024)

Continuous 3D Perception Model with Persistent State
di: Wang, Qianqian, et al.
Pubblicazione: (2025)

SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild
di: Pan, Zhuoyang, et al.
Pubblicazione: (2024)

Segment Any Motion in Videos
di: Huang, Nan, et al.
Pubblicazione: (2025)

Human-level 3D shape perception emerges from multi-view learning
di: Bonnen, Tyler, et al.
Pubblicazione: (2026)

Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction
di: Kerr, Justin, et al.
Pubblicazione: (2024)

Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections
di: Xu, Congrong, et al.
Pubblicazione: (2024)

Generating Continual Human Motion in Diverse 3D Scenes
di: Mir, Aymen, et al.
Pubblicazione: (2023)

The More You See in 2D, the More You Perceive in 3D
di: Han, Xinyang, et al.
Pubblicazione: (2024)

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
di: Yin, Shaofeng, et al.
Pubblicazione: (2026)

Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
di: Li, Xiang, et al.
Pubblicazione: (2025)

Visually Prompted Benchmarks Are Surprisingly Fragile
di: Feng, Haiwen, et al.
Pubblicazione: (2025)

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
di: Mao, Weijia, et al.
Pubblicazione: (2025)

Vinedresser3D: Agentic Text-guided 3D Editing
di: Chi, Yankuan, et al.
Pubblicazione: (2026)

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
di: Yang, Gengshan, et al.
Pubblicazione: (2024)

Toon3D: Seeing Cartoons from New Perspectives
di: Weber, Ethan, et al.
Pubblicazione: (2024)

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
di: Li, Zhengqi, et al.
Pubblicazione: (2024)

Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
di: Li, Xiang, et al.
Pubblicazione: (2024)

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model
di: Wang, Yu, et al.
Pubblicazione: (2026)

Self-Localized Collaborative Perception
di: Ni, Zhenyang, et al.
Pubblicazione: (2024)

Rethinking Score Distillation as a Bridge Between Image Distributions
di: McAllister, David, et al.
Pubblicazione: (2024)

Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
di: Kerr, Justin, et al.
Pubblicazione: (2025)

Towards One-step Causal Video Generation via Adversarial Self-Distillation
di: Yang, Yongqi, et al.
Pubblicazione: (2025)

Reconstructing People, Places, and Cameras
di: Müller, Lea, et al.
Pubblicazione: (2024)

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind
di: Plizzari, Chiara, et al.
Pubblicazione: (2024)

Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation
di: Wang, Pengfei, et al.
Pubblicazione: (2024)

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning
di: Yang, Hui-Yue, et al.
Pubblicazione: (2024)

NeRF-XL: Scaling NeRFs with Multiple GPUs
di: Li, Ruilong, et al.
Pubblicazione: (2024)

How Much 3D Do Video Foundation Models Encode?
di: Huang, Zixuan, et al.
Pubblicazione: (2025)

Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
di: Leijenaar, Remco F., et al.
Pubblicazione: (2025)

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
di: Huang, Zixuan, et al.
Pubblicazione: (2025)

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
di: Chen, Sichen, et al.
Pubblicazione: (2024)

Improving Generative Adversarial Networks with Self-Distillation
di: Nowinowski, Antoni, et al.
Pubblicazione: (2026)

Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation
di: Yu, Sheng-Feng, et al.
Pubblicazione: (2025)

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
di: Jiang, Dengyang, et al.
Pubblicazione: (2026)

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
di: Han, Ruiyan, et al.
Pubblicazione: (2026)

Improving Partially Observed Trajectories Forecasting by Target-driven Self-Distillation
di: Shu, Peng, et al.
Pubblicazione: (2025)

Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
di: Shi, Yuheng, et al.
Pubblicazione: (2025)