Delta: Dense Efficient Long-Range 3D tracking for any video
Tuan Duc Ngo, Peiye Zhuang, Evangelos Kalogerakis, Chuang Gan, Sergey Tulyakov, Hsin-Ying Lee, Chaoyang Wang
Abstract
https://snap-research.github.io/DELTA/ a) Track every pixel from monocular videos b) Consistent in 3D space c) SoTA performance and speed Figure 1: DELTA is a dense 3D tracking approach that (a) tracks every pixel from a monocular video, (b) provides consistent trajectories in 3D space, and (c) achieves state-of-the-art accuracy on 3D tracking benchmarks while being significantly faster than previous methods in the dense setting.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 0094040e-3b36-4a29-ae2e-652a172f6e4aCited by top-tier papers33
- TAPIP3D: Tracking Any Point in Persistent 3D GeometryBowei Zhang, Lei Ke, Adam W. Harley, Katerina FragkiadakiNeurIPS 2025 · 79 citations
- Efficiently Reconstructing Dynamic Scenes One D4RT at a TimeChuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco et al.CVPR 2026 · 52 citations
- Trace Anything: Representing Any Video in 4D via Trajectory FieldsXinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng et al.ICLR 2026 · 38 citations
- Any4D: Unified Feed-Forward Metric 4D ReconstructionJay Karhade, Nikhil Varma Keetha, Yuchen Zhang, Tanisha Gupta et al.CVPR 2026 · 35 citations
- Shape of Motion: 4D Reconstruction From a Single VideoQianqian Wang, Vickie Ye, Hang Gao, Weijia Zeng et al.ICCV 2025 · 29 citations
Builds on25
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 1,248 citations
- Train Short, Test Long: Attention with Linear Biases Enables Input Length ExtrapolationOfir Press, Noah A. Smith, Mike LewisICLR 2022 · 1,168 citations
- Learning to Estimate Hidden Motions with Global Motion AggregationShihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li et al.ICCV 2021 · 402 citations
- GMFlow: Learning Optical Flow via Global MatchingHaofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi et al.CVPR 2022 · 353 citations
- Deep Patch Visual OdometryZachary Teed, Lahav Lipson, Jia DengNeurIPS 2023 · 323 citations
Related papers
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All PixelsJiahao Lu, Weitao Xiong, Jiacheng Deng, Peng Li et al.NeurIPS 2025 · 7 citations
- SpatialTracker: Tracking Any 2D Pixels in 3D SpaceYuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue et al.CVPR 2024 · 40 citations
- Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask TrackingPhuc Nguyen, Minh Luu, Anh Tuan Tran, Cuong Pham et al.CVPR 2025
- Tracking Everything Everywhere All at OnceQianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li et al.ICCV 2023 · 238 citations
- Online Dense Point Tracking with Streaming MemoryQiaole Dong, Yanwei FuICCV 2025 · 1 citation
