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.
hub
VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
38 Pith papers cite this work. Polarity classification is still indexing.
38
Pith papers citing it
abstract
Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, extending these models to large-scale RGB stream 3D reconstruction remains challenging due to memory limitations. In this work, we propose VGGT-Long, a simple yet effective system that pushes the limits of monocular 3D reconstruction to kilometer-scale, unbounded outdoor environments. Our approach addresses the scalability bottlenecks of existing models through a chunk-based processing strategy combined with overlapping alignment and lightweight loop closure optimization. Without requiring camera calibration, depth supervision or model retraining, VGGT-Long achieves trajectory and reconstruction performance comparable to traditional methods. We evaluate our method on KITTI, Waymo, and Virtual KITTI datasets. VGGT-Long not only runs successfully on long RGB sequences where foundation models typically fail, but also produces accurate and consistent geometry across various conditions. Our results highlight the potential of leveraging foundation models for scalable monocular 3D scene in real-world settings, especially for autonomous driving scenarios. Code is available at https://github.com/DengKaiCQ/VGGT-Long.
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
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.
LEXI-SG is the first monocular RGB system for dense open-vocabulary 3D scene graphs that partitions scenes into rooms and performs feed-forward reconstruction per room before global factor-graph alignment.
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
CAL2M achieves calibration-free kilometer-level SLAM by using an assistant eye for scale, epipolar-guided intrinsic correction, and anchor propagation for nonlinear sub-map alignment.
STAC compresses KV caches in streaming 3D reconstruction transformers via temporal token preservation with decayed attention, spatial voxel compression, and chunked multi-frame optimization, delivering 10x memory reduction and 4x faster inference at SOTA quality.
FastVGGT achieves 4x speedup on VGGT for 1000-image inputs using training-free token merging tailored to 3D architectures while reducing error accumulation.
GeoGS-SLAM removes appearance parameters from 3D Gaussian Splatting for geometry-only dense monocular SLAM, achieving faster convergence and fewer primitives while introducing a coherent Sim(3) map update for loop closure.
A real multi-city, multi-kilometer surround-view driving dataset plus an urban-tailored 3DGS baseline shows that city-scale reconstruction still degrades with scale, off-trajectory views, and real-world noise.
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.
VOCA is a causal stereo visual odometry system that achieves state-of-the-art performance on compressed streams by exploiting codec awareness.
Distillation aligns compression mechanisms between full-history and recurrent transformers, enabling linear-time recurrent memory that narrows the performance gap for streaming vision and robotics tasks.
Anchor3R reframes feed-forward 3D reconstruction as current-centric local measurement prediction, using loop-closure and motion averaging to produce coherent global maps from visual streams.
ScaRF-SLAM decouples classical visual SLAM tracking from GFM mapping and adds lightweight scale optimization across submaps to achieve higher trajectory accuracy and 10-20% better reconstruction precision on building-scale indoor and outdoor datasets.
RayDer is a unified transformer backbone for self-supervised static-scene novel view synthesis that absorbs dynamic content as a nuisance factor and shows power-law scaling with data and compute while matching supervised methods in zero-shot settings.
G3T predicts upright pointmaps in gravity-aligned frames and uses the shared vertical axis to reduce rotational degrees of freedom, yielding more accurate incremental 3D reconstructions.
FOUND-IT constructs evolving task-driven 3D scene graphs with on-demand granularity from monocular cameras by augmenting foundation models, reporting 79% higher accuracy on a grounding benchmark and real-time Jetson deployment.
UniT unifies online and offline 3D geometry perception via a Group Autoregressive Transformer that processes observation groups with anchor-free point map prediction and a scale-adaptive loss.
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.
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
Spark3R achieves up to 28x speedup on 1000-frame 3D reconstruction inputs by asymmetrically reducing query and key-value tokens in Vision Transformers while keeping competitive quality.
The paper proposes ray-aware pointer memory with adaptive retain-or-replace updates to improve long-term stability and pose accuracy in streaming 3D reconstruction.
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.
-
CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
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.
-
LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction
LEXI-SG is the first monocular RGB system for dense open-vocabulary 3D scene graphs that partitions scenes into rooms and performs feed-forward reconstruction per room before global factor-graph alignment.
-
PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
-
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
CAL2M achieves calibration-free kilometer-level SLAM by using an assistant eye for scale, epipolar-guided intrinsic correction, and anchor propagation for nonlinear sub-map alignment.
-
STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
STAC compresses KV caches in streaming 3D reconstruction transformers via temporal token preservation with decayed attention, spatial voxel compression, and chunked multi-frame optimization, delivering 10x memory reduction and 4x faster inference at SOTA quality.
-
FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
FastVGGT achieves 4x speedup on VGGT for 1000-image inputs using training-free token merging tailored to 3D architectures while reducing error accumulation.
-
GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM
GeoGS-SLAM removes appearance parameters from 3D Gaussian Splatting for geometry-only dense monocular SLAM, achieving faster convergence and fewer primitives while introducing a coherent Sim(3) map update for loop closure.
-
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
A real multi-city, multi-kilometer surround-view driving dataset plus an urban-tailored 3DGS baseline shows that city-scale reconstruction still degrades with scale, off-trajectory views, and real-world noise.
-
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.
-
VOCA: Visual Odometry with Codec Awareness
VOCA is a causal stereo visual odometry system that achieves state-of-the-art performance on compressed streams by exploiting codec awareness.
-
Compressing Observation History into Agent Memory: Distilling Transformers into Recurrent Transformers
Distillation aligns compression mechanisms between full-history and recurrent transformers, enabling linear-time recurrent memory that narrows the performance gap for streaming vision and robotics tasks.
-
Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping
Anchor3R reframes feed-forward 3D reconstruction as current-centric local measurement prediction, using loop-closure and motion averaging to produce coherent global maps from visual streams.
-
ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM
ScaRF-SLAM decouples classical visual SLAM tracking from GFM mapping and adds lightweight scale optimization across submaps to achieve higher trajectory accuracy and 10-20% better reconstruction precision on building-scale indoor and outdoor datasets.
-
RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
RayDer is a unified transformer backbone for self-supervised static-scene novel view synthesis that absorbs dynamic content as a nuisance factor and shows power-law scaling with data and compute while matching supervised methods in zero-shot settings.
-
G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing
G3T predicts upright pointmaps in gravity-aligned frames and uses the shared vertical axis to reduce rotational degrees of freedom, yielding more accurate incremental 3D reconstructions.
-
FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand
FOUND-IT constructs evolving task-driven 3D scene graphs with on-demand granularity from monocular cameras by augmenting foundation models, reporting 79% higher accuracy on a grounding benchmark and real-time Jetson deployment.
-
UniT: Unified Geometry Learning with Group Autoregressive Transformer
UniT unifies online and offline 3D geometry perception via a Group Autoregressive Transformer that processes observation groups with anchor-free point map prediction and a scale-adaptive loss.
-
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.
-
Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
-
Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction
Spark3R achieves up to 28x speedup on 1000-frame 3D reconstruction inputs by asymmetrically reducing query and key-value tokens in Vision Transformers while keeping competitive quality.
-
Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction
The paper proposes ray-aware pointer memory with adaptive retain-or-replace updates to improve long-term stability and pose accuracy in streaming 3D reconstruction.
-
Geometric Context Transformer for Streaming 3D Reconstruction
LingBot-Map is a streaming 3D reconstruction model built on a geometric context transformer that combines anchor context, pose-reference window, and trajectory memory to deliver accurate, drift-resistant results at 20 FPS over sequences longer than 10,000 frames.
-
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
-
LIST3R: Long-sequence Instance-aware 3D Reconstruction
LIST3R reconnects fragmented video subsequences using persistent instance anchors with semantic and geometric evidence to produce consistent global 3D reconstructions.
-
Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
KiloGS-SLAM is a monocular 3DGS SLAM system with condition-triggered hybrid tracking and probabilistic chunk-based Gaussian mapping that scales to over 10,000 frames in outdoor environments while maintaining accuracy and efficiency.
-
MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization
MoonSplat adds global Sim(3) loop closure and color residual learning to voxelized online 3D Gaussian Splatting for improved monocular camera tracking and rendering quality.
-
Global Structure-from-Motion Meets Feedforward Reconstruction
A new SfM pipeline combining classical and feedforward methods reports state-of-the-art results across multiple datasets and is released as open source.
-
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
-
Real-Scale Island Area and Coastline Estimation using Only its Place Name or Coordinates
A monocular vision system estimates real-scale island area and coastline length with around 10% error using only place name or coordinates input via automated image capture, point cloud generation, and trajectory alignment.
-
ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
ReorgGS reorganizes the Gaussian distribution in converged 3DGS models by resampling centers and covariances to reduce parameterization degeneration and enable better subsequent optimization.
-
MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos
MR.ScaleMaster adds a false-loop alarm and per-session Sim(3) scale estimation to enable accurate multi-agent monocular mapping, showing 7.2x ATE improvement on KITTI with up to 15 agents.
-
MonoEM-GS: Monocular Expectation-Maximization Gaussian Splatting SLAM
MonoEM-GS stabilizes view-dependent geometry from foundation models inside a global Gaussian Splatting representation via EM and adds multi-modal features for in-place open-set segmentation.
-
FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
FrameVGGT maintains stable long-horizon 3D reconstruction, depth, and pose under fixed memory by organizing history as complementary frame-wise KV prototypes plus sparse anchors.
-
TTT3R: 3D Reconstruction as Test-Time Training
TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.
-
Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction
A pipeline using virtual remote sensing from Google Earth Studio, Pi-Long 3D reconstruction, metric alignment, and watershed segmentation estimates forest fuel load as a scalable alternative to traditional surveys.