SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
Geometric Context Transformer for Streaming 3D Reconstruction
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles of Simultaneous Localization and Mapping (SLAM), we introduce LingBot-Map, a feed-forward 3D foundation model for reconstructing scenes from streaming data, built upon a geometric context transformer (GCT) architecture. A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory to address coordinate grounding, dense geometric cues, and long-range drift correction, respectively. This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs over long sequences exceeding 10,000 frames. Extensive evaluations across a variety of benchmarks demonstrate that our approach achieves superior performance compared to both existing streaming and iterative optimization-based approaches.
years
2026 12verdicts
UNVERDICTED 12representative citing papers
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
TRIG factorizes multi-camera poses into ego-trajectory and static rig geometry, with decoupled supervision and sparse temporal-spatial attention, claiming SOTA metric depth, pose, and 3D reconstruction on five driving benchmarks.
3D foundation models enable fast cross-crop 3D reconstruction and phenotyping from sparse smartphone images, cutting average time from 6.52 minutes to 1.58 seconds across 26 sequences.
A two-stage diversity-plus-entropy token selection framework speeds up visual geometry transformers by over 85% on 500-image scenes while preserving baseline accuracy.
LongDPM introduces an overlap-aware chunk-based framework that registers and fuses local dynamic reconstructions to achieve coherent long-range 4D geometry and tracking from monocular video.
NavOne performs one-step global path planning for vision-language navigation by predicting dense path probabilities directly on fused multi-modal top-down maps.
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test
Nano World Models supplies a unified minimalist codebase and evaluation framework for studying diffusion forcing in video prediction across control, games, and robot domains.
SEDualVLN introduces a spatially-enhanced dual-system VLN architecture that achieves state-of-the-art results on VLN-CE benchmarks through coordinated VLM action generation and MLLM waypoint planning.
MemoryWAM is a world action model with a hybrid memory design using recent frames, anchor frames, and gist tokens for efficient long-horizon robotic manipulation.
citing papers explorer
-
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
-
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
-
TRIG: Trajectory-Rig Decoupled Metric Geometry Learning
TRIG factorizes multi-camera poses into ego-trajectory and static rig geometry, with decoupled supervision and sparse temporal-spatial attention, claiming SOTA metric depth, pose, and 3D reconstruction on five driving benchmarks.
-
The Turning Point of 3D Plant Phenotyping: 3D Foundation Models Enable Minute-to-Second Cross-Crop Reconstruction and Beyond
3D foundation models enable fast cross-crop 3D reconstruction and phenotyping from sparse smartphone images, cutting average time from 6.52 minutes to 1.58 seconds across 26 sequences.
-
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
A two-stage diversity-plus-entropy token selection framework speeds up visual geometry transformers by over 85% on 500-image scenes while preserving baseline accuracy.
-
LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
LongDPM introduces an overlap-aware chunk-based framework that registers and fuses local dynamic reconstructions to achieve coherent long-range 4D geometry and tracking from monocular video.
-
NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps
NavOne performs one-step global path planning for vision-language navigation by predicting dense path probabilities directly on fused multi-modal top-down maps.
-
$R^3$: 3D Reconstruction via Relative Regression
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
-
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test
-
Nano World Models: A Minimalist Implementation of Future Video Prediction
Nano World Models supplies a unified minimalist codebase and evaluation framework for studying diffusion forcing in video prediction across control, games, and robot domains.
-
SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
SEDualVLN introduces a spatially-enhanced dual-system VLN architecture that achieves state-of-the-art results on VLN-CE benchmarks through coordinated VLM action generation and MLLM waypoint planning.
-
MemoryWAM: Efficient World Action Modeling with Persistent Memory
MemoryWAM is a world action model with a hybrid memory design using recent frames, anchor frames, and gist tokens for efficient long-horizon robotic manipulation.