"dynamic scene understanding" Papers

15 papers found

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

Vadim Tschernezki, Diane Larlus, Andrea Vedaldi et al.

CVPR 2025arXiv:2506.05546

MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning

Mohammadreza Salehi, Shashanka Venkataramanan, Ioana Simion et al.

ICCV 2025arXiv:2506.08694
2
citations

RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video

ShuHang Xun, Sicheng Tao, Jungang Li et al.

NEURIPS 2025arXiv:2505.02064
5
citations

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

Sen Wang, Jingyi Tian, Le Wang et al.

NEURIPS 2025oral

SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

Mingfei Chen, Zijun Cui, Xiulong Liu et al.

NEURIPS 2025oralarXiv:2506.05414
5
citations

Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

Ruiping Liu, Junwei Zheng, Yufan Chen et al.

NEURIPS 2025arXiv:2510.11509

Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding

Seong Hyeon Park, Jinwoo Shin

NEURIPS 2025oral

Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

David Yifan Yao, Albert J. Zhai, Shenlong Wang

CVPR 2025highlightarXiv:2503.21761
14
citations

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

Shijie Zhou, Alexander Vilesov, Xuehai He et al.

ICCV 2025arXiv:2508.02095
16
citations

DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)

Zongxin Yang, Guikun Chen, Xiaodi Li et al.

ICML 2024oralarXiv:2401.08392
64
citations

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

Weirong Chen, Le Chen, Rui Wang et al.

CVPR 2024arXiv:2401.01887
46
citations

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

Hoang Chuong Nguyen, Tianyu Wang, Jose M. Alvarez et al.

CVPR 2024arXiv:2404.14908
2
citations

PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation

Yue-Jiang Dong, Yuan-Chen Guo, Ying-Tian Liu et al.

AAAI 2024paperarXiv:2312.13066
9
citations

ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion

Sungmin Woo, Wonjoon Lee, Woo Jin Kim et al.

ECCV 2024arXiv:2407.09303
6
citations

Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence

Ripon Saha, Dehao Qin, Nianyi Li et al.

CVPR 2024arXiv:2404.13605
9
citations