paper-with-me

홈 › Papers

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

2026-03-04 · Haian Jin, Rundi Wu, Tianyuan Zhang, Ruiqi Gao, Jonathan T. Barron, Noah Snavely, Aleksander Holynski arxiv

Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $π^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when applied to large image collections. Sequential-reconstruction approaches reduce this cost but sacrifice reconstruction quality. We introduce ZipMap, a stateful feed-forward model that achieves linear-time, bidirectional 3D reconstruction while matching or surpassing the accuracy of quadratic-time methods. ZipMap employs test-time training layers to zip an entire image collection into a compact hidden scene state in a single forward pass, enabling reconstruction of over 700 frames in under 10 seconds on a single H100 GPU, more than $20\times$ faster than state-of-the-art methods such as VGGT. Moreover, we demonstrate the benefits of having a stateful representation in real-time scene-state querying and its extension to sequential streaming reconstruction.

📄 PDF Abstract BibTeX arXiv:2603.04385

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Sleep-time Compute: Beyond Inference Scaling at Test-time

2025-04-17 · Kevin Lin, Charlie Snell, Yu Wang, Charles Packer 외

Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allo…

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

2018-12-13 · Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma 외

Deep learning (DL) defines a data-driven programming paradigm that automatically composes the system decision logic from the training data. In company with the data explosion and hardware acceleration during the past dec…

Deep LearningSpeech-to-Text

Stateful ODE-Nets using Basis Function Expansions

2021-06-21 · NeurIPS 2021 12 · Alejandro Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

The recently-introduced class of ordinary differential equation networks (ODE-Nets) establishes a fruitful connection between deep learning and dynamical systems. In this work, we reconsider formulations of the weights a…

image-classificationImage ClassificationSentence

How to Learn when Data Gradually Reacts to Your Model

2021-12-13 · Zachary Izzo, James Zou, Lexing Ying

A recent line of work has focused on training machine learning (ML) models in the performative setting, i.e. when the data distribution reacts to the deployed model. The goal in this setting is to learn a model which bot…

Koopman Identification of Nonlinear Systems via Reservoir Liftings

2026-05-06 · Weibin Gu, Chen Yang, Lu Shi arxiv

Learning tractable linear representations of nonlinear dynamical systems via Koopman operator theory is often hindered by dictionary selection, temporal memory encoding, and numerical ill-conditioning. Inspired by Reserv…