LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Junyi Zhang; Charles Herrmann; Junhwa Hur; Chen Sun; Ming-Hsuan Yang; Forrester Cole; Trevor Darrell; Deqing Sun

cs.CVMar 3, 2026

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Authors: Junyi Zhang, Charles Herrmann, Junhwa Hur, Chen Sun, Ming-Hsuan Yang, Forrester Cole, Trevor Darrell, Deqing Sun

Organizations: Google DeepMind · UC Berkeley

Abstract

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization. LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning. To manage the critical challenge of coherence across chunk boundaries, we propose a learning-based hybrid memory module. This dual-component system combines a parametric Test-Time Training (TTT) memory to anchor the global coordinate frame and prevent scale drift, alongside a non-parametric Sliding Window Attention (SWA) mechanism to preserve uncompressed context for high-precision adjacent alignment. Remarkably, this memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference. Evaluated across standard benchmarks and a newly repurposed VBR dataset with sequences of up to 19k frames, LoGeR substantially outperforms prior state-of-the-art feedforward methods--reducing ATE on KITTI by over 74%--and achieves robust, globally consistent reconstruction over unprecedented horizons.

Figures & tables

Mechanism	Compute Cost	Local Context	Global Context
Full Attention	$\mathcal{O}(N^{2})$	Lossless	Lossless
Sliding Window Attn.	$\mathcal{O}(N)$	Lossless	Limited
TTT / Linear Attn.	$\mathcal{O}(N)$	Compressed	Compressed
Ours (Hybrid Memory)	$\mathcal{O}(N)$	Lossless	Compressed

Table 1: Architectural trade-offs in sequence modeling. Our hybrid memory module achieves a balance, preserving lossless local geometric details while maintaining global structural consistency at a linear computational cost with respect to sequence length.

Figure 2: Overview of a single block of our hybrid memory module. We process the input sequence in consecutive chunks of frames. While each block utilizes frame and bidirectional attention from prior work, we introduce new components to effectively propagate information across the entire sequence. Specifically, we incorporate Sliding Window Attention to improve consistency between neighboring chunks, and Test-Time Training layers to maintain long-range, global consistency across all chunks.

Figure 3: Comparison of different methods across varying sequence lengths and scene scales. Although FastVGGT is able to process a larger number of frames during inference, it fails completely on large-scale scenes, highlighting the inherent “data wall” of models trained strictly on short-context bubbles. In contrast, LoGeR breaks both the context and data walls by pairing a hybrid memory architecture with diverse long-horizon training data.

	Methods	00	01	02	03	04	05	06	07	08	09	10	Avg.
	num. of frames, scale	4542, 3.7km	1101, 2.5km	4661, 5.1km	801, 0.6km	271, 0.4km	2761, 2.2km	1101, 1.2km	1101, 0.7km	4071, 3.2km	1591, 1.7km	1201, 0.9km	-
	Contains Loop?	✓	$\times$	✓	$\times$	$\times$	✓	✓	✓	$\times$	✓	$\times$	-
Opt.-based	DROID-SLAM ( Teed & Deng, 2021 )	92.10	344.60	107.61	2.38	1.00	118.50	62.47	21.78	161.60	72.32	118.70	100.28
	DPV-SLAM ( Lipson et al., 2024 )	112.80	11.50	123.53	2.50	0.81	57.80	54.86	18.77	110.49	76.66	13.65	53.03
	DPV-SLAM++ ( Lipson et al., 2024 )	8.30	11.86	39.64	2.50	0.78	5.74	11.60	1.52	110.90	76.70	13.70	25.75
	VGGT-Long ( Deng et al., 2025 )	8.67	121.17	32.08	6.12	4.23	8.31	5.34	4.63	53.10	41.99	18.37	27.64

Table 2: Comparison of Absolute Trajectory Error (ATE

\downarrow

, m) on KITTI. The top and bottom blocks denote optimization-based and feedforward methods, respectively. Bold and underline indicate the best and second-best performance among feedforward methods. LoGeR* denotes a variant of our method with feedforward pose alignment for both training and inference.

Figure 4: Quantitative results on our proposed VBR ( Brizi et al., 2024 ) evaluation showing results on very long sequences spanning from 1,000 to 19,000 frames. Our methods achieve 55.2% more accurate results than prior methods.

Figure 5: Qualitative camera trajectories on the VBR dataset. LoGeR accurately preserves global scale and trajectory over very long sequences, closely matching the ground truth where prior methods suffer from severe drift.

Figure 8: Qualitative results on ScanNet and TUM-Dynamics. While the proposed Pi3-Chunk baseline yields slightly better pose metrics on small-scale TUM sequences (unlike its severe drift on longer trajectories), LoGeR produces visually superior reconstructions. As highlighted, LoGeR accurately recovers structural details, avoiding the severe distortions and geometric artifacts present in baselines.

Figure 9: Q uantitative results on camera pose evaluation , demonstrating that both our proposed baseline and LoGeR substantially outperform prior work, with 80.0% and 66.1% relative gains on ScanNet and TUM datasets, respectively.

Figure 10: Ablation of disabling SWA or TTT at inference time. SWA ensures geometric consistency between adjacent chunks (local consistency), and lacking it causes noticeable local misalignment artifacts. Meanwhile, TTT maintains the global context (global consistency); without it, the model suffers from severe trajectory drift over long horizons.

	ScanNet		TUM
Method	500f	1000f	500f	1000f
LoGeR	0.087	0.107	0.033	0.050
w/o TTT	0.108	0.162	0.043	0.079
w/o SWA	0.115	0.143	0.039	0.053
All datasets	0.087	0.107	0.033	0.050
w/o 5 large datasets	0.102	0.156	0.050	0.072

Table 3: Comparison of baseline and ablation results across ScanNet (subset) and TUM datasets. We report the results of ATE (

\downarrow

) on both 500 and 1000 frames of sequences.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Percentage (%)
DL3DV ( Ling et al., 2024 )	17.89
TartanAirV2 ( Patel et al., 2025 )	17.89
OmniWorld-Game (subset) ( Zhou et al., 2025 )	17.89
ARKitScenes ( Baruch et al., 2021 )	10.44
TartanAir ( Wang et al., 2020 )	8.94
Waymo ( Schwall et al., 2020 )	6.71

Appendix

Table 4: Training data mixture. We list the datasets used in our final training configuration along with their relative sampling percentages. Navigation and large-scale scene datasets are heavily weighted to encourage long-range geometric reconstruction.

Chunk Size	Speed (FPS)	Memory (GB)
64	9.3	27.2
48	10.6	22.3
32	12.1	18.1

Appendix

Table 5: Inference efficiency. Measured on a single NVIDIA A100 (40GB) GPU over a 500-frame sequence with varying chunk sizes. As the number of frames increases, the speed improves slightly, while memory consumption remains constant.

	Methods	colosseo_0	campus_0	campus_1	pincio_0	spagna_0	diag_0	ciampino_1	Avg.
	num. of frames, scale	8815, 1.45km	12042, 2.73km	11671, 2.95km	11142, 1.27km	14141, 1.56km	10021, 1.02km	18846, 5.20km	-
Opt.	VGGT-SLAM ( Maggio et al., 2025 )	102.92	110.77	89.69	72.98	62.67	35.62	144.02	88.38
	VGGT-Long w/o LC ( Deng et al., 2025 )	86.46	132.66	115.65	64.40	57.39	33.66	186.13	96.62
	VGGT-Long ( Deng et al., 2025 )	45.73	132.68	115.65	64.40	58.49	33.66	187.97	91.23
Feedforward	InfiniteVGGT ( Yuan et al., 2026 )	90.02	136.83	116.69	77.72	63.47	33.91	202.11	102.96
	CUT3R ( Wang et al., 2025b )	88.16	46.39	48.00	52.87	47.98	30.18	187.58	71.59

Appendix

Table 6: Comparison of Absolute Trajectory Error (ATE

\downarrow

, m) on VBR. The top and bottom blocks denote optimization-based and feedforward methods, respectively. Bold and underline indicate the best and second-best performance among feedforward methods.

Figure 11: Quantitative results of video depth estimation on the Bonn dataset. Both our proposed baseline (Pi3-Chunk) and LoGeR significantly outperform prior works. Note that VGGT and StreamVGGT are omitted after certain frames due to out-of-memory (OOM).

Figure 12: 3D reconstruction results on the 7-Scenes dataset , uniformly sampling 100, 500, and 1k frames. For the evluation of 1k frames, our method achieves a 90.3% and 72.1% performance boost (error reduction) with comparable runtimes against concurrent works TTT3R ( Chen et al., 2026 ) and VGG-T 3 ( Elflein et al., 2026 ) , respectively. LoGeR also achieves 84.1% faster inference speed compared to VGGT with 31.0% better performance.

Figure 13: Qualitative results on KITTI. Ours shows more accurate long trajectory estimation.

Figure 14: Qualitative results on large-scale outdoor and indoor scenes , showing minutes-long long-horizon reconstruction results.

Explore similar work

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
May 10, 2026Zichen Zou, Xiaosong Jia, Zuxuan Wu +13D ViTs Streaming 3D Reconstruction
Institute of Trustworthy Embodied AI (TEAI), Fudan University · 2Shanghai Key Laboratory of Multimodal Embodied AI
Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction
Sep 18, 2026Jingke Zhou, Chenhang Ma, Zhizhou Zhong +63D Reconstruction Streaming 3D Reconstruction
Zhejiang University · Fudan University · Peking University +1
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
May 22, 2026Chong Cheng, Peilin Tao, Nanjie Yao +93D ViTs Streaming 3D Reconstruction
HKUST(GZ) · Horizon Robotics · CASIA +2

May 10, 2026J/K move · Enter open · S save

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

Zichen Zou, Xiaosong Jia, Zuxuan Wu, Yu-Gang Jiang

Institute of Trustworthy Embodied AI (TEAI), Fudan University · 2Shanghai Key Laboratory of Multimodal Embodied AI

3D ViTs Streaming 3D Reconstruction 3D Reconstruction Multi-View 3D Reconstruction Efficient Attention

Open paper AskPDF arXiv

Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal attention, yet its KV cache grows linearly with frames, causing memory overflow and quality degradation. We present RetrieveVGGT, a training-free framework, which formulates context construction for VGGT as a retrieval problem. By retrieving a fixed number of relevant frames at each step, VGGT maintains a controllable memory budget, which is close to its training context length. Interestingly, we find that the similarity between current frame queries and cached history frame keys at the first global attention layer of VGGT is already a strong indicator of relevance, eliminating the need for additional learned scoring. To enhance information diversity similar to a recommender system, we propose Segment Sampling so that the retrieval spans distinct relevant segments rather than a single high-similarity region. We design a pose-aware spatial memory mechanism that organizes history frames according to their already estimated camera poses, enabling location-aware retrieval. Extensive experiments demonstrate that RetrieveVGGT achieves state-of-the-art performance, outperforming StreamVGGT, TTT3R, and InfiniteVGGT while maintaining constant memory usage regardless of sequence length. Code is available at https://github.com/zzctmd/RetrieveVGGT.

Abstract

Explore similar work

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

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

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction