paper-with-me

Papers

3D Reconstruction with Spatial Memory

2024-08-28 · Hengyi Wang, Lourdes Agapito

We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any prior knowledge of the scene or camera parameters. Unlike DUSt3R, which predicts per image-pair pointmaps each expressed in its local coordinate frame, Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment. The key idea of Spann3R is to manage an external spatial memory that learns to keep track of all previous relevant 3D information. Spann3R then queries this spatial memory to predict the 3D structure of the next frame in a global coordinate system. Taking advantage of DUSt3R's pre-trained weights, and further fine-tuning on a subset of datasets, Spann3R shows competitive performance and generalization ability on various unseen datasets and can process ordered image collections in real time. Project page: \url{https://hengyiwang.github.io/projects/spanner}

📄 PDF Abstract BibTeX arXiv:2408.16061

Code (1)

hengyiwang/spann3r pytorch

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Latent Spatial Memory for Video World Models

2026-06-08 · Weijie Wang, Haoyu Zhao, Yifan Yang, Feng Chen 외 arxiv

Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computationally expensive, requiring repeated re…

Video Generation

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning

2026-05-31 · Jixuan He, Xueting Li, Chieh Hubert Lin, Ming-Hsuan Yang arxiv

Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reasoning, directional comparison, and distanc…

Spatial Reasoning3D ReconstructionPoint Clouds

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

2025-07-03 · Yuqi Wu, Wenzhao Zheng, Jie Zhou, Jiwen Lu arxiv

Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, wh…

3D Reconstruction

mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies

2025-09-24 · Remo Steiner, Alexander Millane, David Tingdahl, Clemens Volk 외 arxiv

End-to-end learning of robot control policies, structured as neural networks, has emerged as a promising approach to robotic manipulation. To complete many common tasks, relevant objects are required to pass in and out o…

3D Reconstruction

MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction

2026-03-16 · Jiacheng Dong, Huan Li, Sicheng Zhou, Wenhao Hu 외 arxiv

Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial perception, yet existing recurrent online…

3D Reconstruction