Seurat: From Moving Points to Depth
Seokju Cho, Jiahui Huang, Seungryong Kim, Joon-Young Lee
2025年份
8顶会引用
摘要
Adobe Research 3D Trajectories Figure 1. Seurat predicts precise and smooth depth changes for dynamic objects over time by only looking at the 2D point trajectories, which encode depth cues in their motion patterns. The figure illustrates 2D point tracks lifted into 3D space with our depth predictions on videos from the DAVIS dataset [41].
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 Paper8
- Emergent Temporal Correspondences from Video Diffusion TransformersJisu Nam, Soowon Son, Dahyun Chung, Jiyoung Kim 等NeurIPS 2025 · 被引用 30 次
- Generative Video Motion Editing with 3D Point TracksYao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang 等CVPR 2026 · 被引用 23 次
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All PixelsJiahao Lu, Weitao Xiong, Jiacheng Deng, Peng Li 等NeurIPS 2025 · 被引用 7 次
- AnthroTAP: Learning Point Tracking with Real-World MotionInès Hyeonsu Kim, Seokju Cho, Jahyeok Koo, Junghyun Park 等CVPR 2026 · 被引用 5 次
- DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry EstimationTuan Duc Ngo, Jiahui Huang, Seoung Wug Oh, Kevin Blackburn-Matzen 等CVPR 2026 · 被引用 3 次
它引用的顶会 Paper22
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- MLP-Mixer: An all-MLP Architecture for VisionIlya O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer 等NeurIPS 2021 · 被引用 3,862 次
- ViViT: A Video Vision TransformerAnurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun 等ICCV 2021 · 被引用 2,947 次
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 被引用 1,248 次
相关 Paper
- SpatialTracker: Tracking Any 2D Pixels in 3D SpaceYuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue 等CVPR 2024 · 被引用 40 次
- Swept volumes via spacetime numerical continuationSilvia Sellán, Noam Aigerman, Alec JacobsonSIGGRAPH 2021 · 被引用 35 次
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular VideosWen-Hsuan Chu, Lei Ke, Katerina FragkiadakiNeurIPS 2024 · 被引用 75 次
- AdaDepth: Exploiting Inherent Scene Information for Self-Supervised Depth Estimation in Dynamic ScenesXuanang Gao, Xiongbin Wu, Zhiwei Ning, Runze Yang 等AAAI 2026
- SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene ReconstructionJihwan Yoon, Sangbeom Han, Jaeseok Oh, Minsik LeeICLR 2025
