Skip to content
Preprint

Info3R: Information-Adaptive Test-Time Training for 3D Reconstruction

Sep 2026 · 0 citations · 21 references
Computer Science

Abstract

Transformer-based models have recently achieved strong performance on 3D reconstruction from images, and recent works extend them to process video streams in an online manner for real-world deployment. However, existing methods overlook two key signals when handling long image streams: the importance of each incoming frame and the information saturation of the model's internal state. In this paper, we propose Info3R, a novel information-adaptive test-time training method for the online 3D reconstruction. We introduce an information-aware state update that modulates the state update strength based on the redundancy and informativeness of each incoming frame. To restore the state's plasticity -- its capacity to incorporate new observations -- we propose a dynamic state reset, triggered by the cumulative magnitude of state updates and the model's prediction confidence and accompanied by an anchor-to-world alignment. Our method achieves consistent improvements on camera pose estimation, video depth estimation, and 3D reconstruction, while substantially mitigating the performance degradation in the long sequence evaluation. Notably, on KITTI Odometry, our method achieves on average 1.68x lower ATE than LongStream, demonstrating its robustness on extended outdoor sequences.

View source

Similar papers

Preprint Oct 2026

VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction

Feed-forward 3D vision models such as VGGT have achieved remarkable progress, unifying camera estimation and dense scene reconstruction in a single pass. However, their quadratic global attention makes long image sequences expensive, while existing sparse methods may favor highly attended yet value-redundant regions. T...

Jun-Yi Wu, Fan-Qing Kong, Le-Yang Chen et al. · 0 citations
Sep 2026

OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute

Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research groups and precludes edge deployment. Additionally, generating 3D supervision without sensors still relies on slow, unreliable Structure-from-Motion, as the community lacks...

Brandon Leblanc, Charalambos Poullis · 0 citations
Preprint Sep 2026

DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming

DecoGS introduces an adaptive mechanism that selectively focuses optimization on spatiotemporal regions exhibiting motion or photometric changes, eliminating redundant updates that cause flickering and drift in nominally static regions, while enabling fast, high-fidelity scene updates.

Idil Sulo, Alexey Supikov, Ilke Demir et al. · 0 citations
Preprint Oct 2026

Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models

The key insight is that DA3's cross-view features, though trained only for depth consistency, implicitly encode motion-discriminative signals when combined with best-match feature search across frames, which could enable much denser temporal sampling that prior methods cannot support.

Xin-Hao Xiang, Wei-Yang Li, Zhi-Jie Zheng et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction

This work proposes LoG-VGGT, a memory-efficient framework for long-sequence 3D reconstruction that balances local temporal modeling with global camera consistency, and introduces cross-window attention at a small subset of transformer blocks, enabling effective information propagation across adjacent temporal windows w...

Jing-Ke Zhou, Chen-Hang Ma, Zhi-Zhou Zhong et al. · 1 citation
Preprint Oct 2026

S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens

Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evidence and remain renderable as observations arrive. Latent spatial tokens offer a promising representation for this purpose, but constructing them from an image collection...

Fang Li, Jiraphon Yenphraphai, Quentin Herau et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.