MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization

Nobel Dang; Bing Li

cs.CVMar 28, 2026

MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization

Authors: Nobel Dang, Bing Li

Organizations: Clemson University, SC, USA

Abstract

Relative camera pose is a basic geometric cue for visual re-localization and scene understanding. When using images alone, visual evidence may not sufficiently support reliable estimation of 3D-consistent motion. The challenge is especially acute in unfamiliar and ever-changing environments for real-time applications, where a system must infer spatial structure under tight time constraints from what it sees rather than rely on scene-specific reconstruction or training. This raises a fundamental question: how can live 3D camera motion be estimated accurately for re-localization in unseen environments while drawing on enough scene context to resolve pose ambiguity? We introduce MultiLoc, a multi-view-guided relative pose regressor trained at scale to achieve spatial and geometric consistent representations for robust visual re-localization in unseen scenarios with high inference speed. Specifically, MultiLoc creates a minimal 3D-sub-scene representation of the environment and efficiently transforms it into 3D spatially and geometrically consistent features in a single forward pass, enabling precise pose estimates with high inference speed gains. Across diverse indoor, outdoor, and in-the-wild visual re-localization benchmarks---Indoor6, Cambridge Landmarks and WaySpots---MultiLoc consistently outperforms state-of-the-art relative pose regression methods. We also highlight that MultiLoc, a pose regressor, also performs competitively with inference-heavy and structure-based approaches while retaining sub-second inference and generalizing to unseen scenes. Given a small posed support set, it also surpasses relative pose regression, feature-matching, and non-regression methods on several relative camera pose benchmarks. Code will be released.

Figures & tables

Figure 1: One forward pass, no scene-training or map. Given a query and $K$ reference images with 6-DoF poses—a camera constellation, or 3D sub-scene (left)—MultiLoc achieves sub-scene consistent spatial and geometric representations by jointly fusing multi-view images and the available poses. By doing so, just with a single forward pass, MultiLoc matches the accuracy of feature matching (MC) and scene-coordinate regression (SCR) methods while offering one of the fastest inference speed across all the baselines on Indoor-6 (right).

Figure 2: MultiLoc Architecture overview. The retrieved images’ extrinsics are embedded via our camera encoders into camera tokens $y$ and added with learnable camera tokens $l$ , while all images pass through DINO-v2 to obtain patch tokens. All the tokens are then concatenated and processed by alternating-attention (AA) transformer blocks. Finally, camera tokens are used to predict relative poses between query and reference images using the camera head and metric scale is recovered by the pre-computed scene-scale $s$ . The red arrows denote the flow of camera tokens.

	Method	ACID			MegaDepth-1500			ScanNet-1500
	Method	$5^{\circ}$	$10^{\circ}$	$20^{\circ}$	$5^{\circ}$	$10^{\circ}$	$20^{\circ}$	$5^{\circ}$	$10^{\circ}$	$20^{\circ}$
	Efficient LoFTR	–	–	–	52.80	69.19	81.18	19.20	37.00	53.60
	RoMa	57.98	68.53	76.62	60.92	75.63	85.69	34.13	55.28	71.69
	DUSt3R	21.50	35.95	49.70	27.90	46.00	63.30	23.81	45.91	65.57
	MASt3R (Ess.)	54.42	66.23	75.26	42.79	62.55	77.61	35.25	57.64	74.48
Pair	NoPoSplat	48.60	61.70	72.80	–	–	–	31.80	53.80	71.70

Table 1: Relative camera pose estimation results on ACID, MegaDepth-1500, and ScanNet-1500. Non-PR denotes non-pose-regression methods, and PR relative pose regression. Shaded rows use multiple views; unshaded rows are pairwise. Red indicates the best and bold the second-best result.

Panel of Figure 3 — Figure 3: Visual re-localization on the Indoor-6 benchmark. (a) Top row shows the query and retrieved reference images . Bottom row shows the Indoor6 reconstruction, where MultiLoc’s predicted pose closely matches the ground truth in position and orientation. Blue frustums indicate reference poses. (b) Median translation / rotation error averaged over six scenes (cm / ∘ ; lower is better) and per-query latency; bold is best within each category. Per-scene results are in appendix.

Figure 4: MultiLoc v/s ReLoc3r trajectory error depiction on GreatCourt sequence of Cambridge dataset. Gray dashed lines indicate the translational error between ground truth and predicted poses. MultiLoc achieves significantly lower error by leveraging 3D sub-scene context from multiple images and their pose, whereas ReLoc3r’s reliance on pairwise images lead to higher drift.

Category	Method	GreatCourt	Kings	OldHosp	ShopFac	StMary	Avg	Map. Time	Latency
MC	MASt3R + Kapture	0.10 / 0.10	0.08 / 0.12	0.13 / 0.24	0.03 / 0.13	0.04 / 0.12	0.08 / 0.14	$>10min$	0.85 s
MC	E5+1 (RoMa)	0.37 / 0.16	0.21 / 0.35	0.29 / 0.64	0.07 / 0.27	0.11 / 0.37	0.21 / 0.36	$<1min$	7.30 s
SCR	ACE	0.44 / 0.20	0.31 / 0.40	0.30 / 0.60	0.06 / 0.30	0.20 / 0.60	0.26 / 0.42	$>2min$	$\sim$ 0.10 s
SCR	GLACE	0.19 / 0.10	0.19 / 0.30	0.18 / 0.40	0.05 / 0.20	0.10 / 0.30	0.14 / 0.26	$>9min$	$\sim$ 0.10 s
RPR	ReLoc3r	1.22 / 0.73	0.42 / 0.36	0.62 / 0.55	0.13 / 0.58	0.34 / 0.58	0.55 / 0.56	$<1min$	0.23 s
	GeLoc3r	1.07 / 0.52	0.41 / 0.34	0.64 / 0.54	0.15 / 0.64	0.27 / 0.58	0.51 / 0.52	$<1min$	–

Table 2: Visual re-localization benchmark on Cambridge Landmarks with median errors as (m / ∘ ). Green, blue, and red cells indicate the best, middle, and worst comparative results, respectively.

Categ.	Method	Bears	Cubes	Insc	Lawn	Map	SqB	Statue	Tendrils	Rock	WinterSign	Avg
MC	E5+1 (RoMa)	2.2 / 0.72	8.0 / 0.85	7.9 / 1.00	11.6 / 3.29	7.7 / 0.92	12.3 / 0.74	59.3 / 1.48	22.2 / 3.59	3.1 / 0.73	170.0 / 1.55	30.4 / 1.49
SCR	ACE	3.6 / 1.15	5.3 / 0.76	10.0 / 1.50	120.0 / 37.00	7.5 / 1.10	5.7 / 0.70	595.0 / 15.70	166.0 / 45.70	2.9 / 0.74	423.0 / 1.19	134.0 / 10.55
SCR	GLACE	3.0 / 0.90	5.9 / 0.80	10.0 / 1.30	115.0 / 26.30	7.2 / 1.00	5.7 / 0.70	517.0 / 10.30	155.0 / 32.20	3.2 / 0.80	465.0 / 1.30	128.7 / 7.56
RPR	ReLoc3r	13.1 / 3.63	69.4 / 2.14	33.0 / 3.28	41.5 / 11.03	16.4 / 2.00	27.7 / 1.73	331.2 / 11.00	82.9 / 15.31	8.3 / 1.34	607.0 / 5.15	123.1 / 5.66
RPR	MultiLoc (ours)	4.0 / 0.77	8.3 / 0.93	9.2 / 1.09	16.0 / 2.84	6.9 / 1.12	9.9 / 0.75	89.0 / 1.46	34.0 / 3.55	4.9 / 0.72	65.0 / 2.61	24.7 / 1.58

Table 3: Visual re-localization benchmark on the WaySpots dataset in median translation / rotation error as (cm / ∘ ). MASt3R+Kapture is omitted because it’s superset, Map-Free, was used to train it.

Figure 5: Visual Localization performance (average across all scenes) and inference speed comparison across varying numbers of input views (k) on the Cambridge Landmarks.

	Visual Reloc.		Camera Pose Est.
State	Cambridge	WaySpots	ACID	ScanNet-1500
Frozen (no pose)	41.0 / 0.374	66.6 / 1.80	22.55 / 40.85	38.82 / 60.31
MultiLoc (with pose)	29.5 / 0.35	24.7 / 1.39	76.56 / 87.15	62.34 / 76.32

Table 4: Median pose error [cm / ∘ ] for visual re-localization (all 5 Cambridge, 10 WaySpots sequences) and AUC@5/10 for camera pose estimation (ACID, ScanNet-1500). : frozen (no pose intrusion); : trained MultiLoc. Red denotes best, blue second best result.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Ablation study for MultiLoc’s architecture . Using learnable camera token only for the last image (top) leads to unstable training and sudden gradient jumps. Whereas, using learnable tokens for all the images in a sequence (bottom) and regressing upon them reduces this instability.

Methods	GreatCrt	KingsClg	OldHosp	ShopFac	StMarys	Avg Rot ( ∘ $\downarrow$ )	Avg Trans. (m $\downarrow$ )
Umeyama Align.	0.44 / 0.37	0.33 / 0.41	0.39 / 0.70	0.09 / 0.33	0.23 / 0.51	0.46	0.30
Motion Avg.	0.45 / 0.25	0.32 / 0.33	0.40 / 0.52	0.08 / 0.28	0.24 / 0.36	0.35	0.30
Scale ( $s$ )	0.45 / 0.26	0.32 / 0.32	0.39 / 0.53	0.08 / 0.29	0.23 / 0.37	0.35	0.29

Appendix

Table 5: Scale Recovery benchmark of MultiLoc (ours) on Cambridge dataset for visual re-localization. Median translation error is in meters (m) and median rotation error in degrees ( ∘ ).

Figure 7: RoMA comparison. Pairwise (top) vs. best-reference (bottom) matching. While additional views increased inliers from 2437 to 2999 (top left in red), pose error, max(trans,rot), rose from 1.90 $\circ$ to 3.21 $\circ$ showing failure to exploit multi-view cues.

Category	Method	Scene1	Scene2a	Scene3	Scene4a	Scene5	Scene6	Avg
MC	MASt3R + Kapture	3.4 / 0.31	3.4 / 0.15	2.9 / 0.28	2.5 / 0.39	4.2 / 0.45	2.3 / 0.23	3.1 / 0.30
MC	E5+1 (RoMa)	2.2 / 0.43	2.1 / 0.23	1.5 / 0.37	3.0 / 0.68	3.8 / 0.65	1.3 / 0.31	2.3 / 0.45
SCR	ACE	17.7 / 2.40	8.0 / 0.80	9.0 / 1.60	4.6 / 0.90	21.6 / 4.00	5.2 / 0.90	11.0 / 1.80
SCR	GLACE	3.8 / 0.70	3.9 / 0.40	2.9 / 0.60	2.3 / 0.50	6.1 / 0.90	2.1 / 0.40	3.5 / 0.60
	FastForward	–	–	–	–	–	–	4.0 / 0.60
RPR	ReLoc3r	8.0 / 0.60	11.0 / 0.78	4.0 / 0.44	9.0 / 0.87	29.0 / 1.60	3.0 / 0.52	10.7 / 0.80

Appendix

Table 6: Visual re-localization benchmark on the Indoor-6 dataset. We report median translation / rotation error (cm / ∘ ); lower is better. The best result within each category is in bold . “–” denotes results not yet available.

Category	Method	GreatCourt	Kings	OldHosp	ShopFac	StMary	Avg
MC	HLoc (SP+SG)	0.16 / 0.10	0.12 / 0.20	0.15 / 0.30	0.04 / 0.20	0.07 / 0.20	0.11 / 0.20
MC	MASt3R + Kapture	0.10 / 0.10	0.08 / 0.12	0.13 / 0.24	0.03 / 0.13	0.04 / 0.12	0.08 / 0.14
	E5+1 (RoMa)	0.37 / 0.16	0.21 / 0.35	0.29 / 0.64	0.07 / 0.27	0.11 / 0.37	0.21 / 0.36
SCR	ACE	0.44 / 0.20	0.31 / 0.40	0.30 / 0.60	0.06 / 0.30	0.20 / 0.60	0.26 / 0.42
SCR	GLACE	0.19 / 0.10	0.19 / 0.30	0.18 / 0.40	0.05 / 0.20	0.10 / 0.30	0.14 / 0.26
	FastForward	0.62 / 0.40	0.24 / 0.40	0.26 / 0.50	0.08 / 0.40	0.14 / 0.50	0.27 / 0.40

Appendix

Table 7: Visual re-localization benchmark on the Cambridge Landmarks dataset in median translation / rotation error as (m / ∘ ). Green, blue, and red cells indicate the best, middle, and worst comparative results, respectively.

Figure 8: Failure cases when retrieved images are not co-visible. The following cases illustrate scenarios where co-visibility-based retrieval features fail to identify appropriate reference images. We demonstrate using top-5 of 10 such reference images per query. Such instances result in significant translation ( purple dashed line ) and rotation errors between the ground truth and predicted camera poses.

Relative Pose Estimation

Relative pose estimation recovers the rotation and translation between cameras, objects, or robots from visual and other sensor measurements.

See all 62 papers

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization
Jun 23, 2026Zhaopeng Cui, Jiarui Hu, Jingbo Liu +7Camera Pose Estimation 3D Scene Understanding
1State Key Lab of CAD&CG, Zhejiang University · 2Ant Group
$L^3$ :Scene-agnostic Visual Localization in the Wild
Mar 9, 2026Yu Zhang, Muhua Zhu, Yifei Xue +2Robot Localization
Hunan University, Changsha, Hunan 410082, China
VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graph
Sep 18, 2026Qianru Li, Xuyang Chen, Xuqin Wang +6Camera Pose Estimation Map-Based Localization
Technical University of Munich, Munich, Germany · Huawei Hilbert Research Center (Dresden), Germany

Jun 23, 2026J/K move · Enter open · S save

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization

Zhaopeng Cui, Jiarui Hu, Jingbo Liu, Boming Zhao+6

1State Key Lab of CAD&CG, Zhejiang University · 2Ant Group

Camera Pose Estimation 3D Scene Understanding

Open paper AskPDF arXiv

Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes, struggling to perceive scene semantics and compositions, which limits both interpretability and applicability. In this paper, we explore the issue of how to organize rich object information in a scene, including semantics, layout, and geometry, into a structured map representation, thereby utilizing object units exclusively to drive the camera relocalization task. To this end, we propose OpenReLoc, a camera relocalization system designed to provide scene understanding and accurate pose estimation capabilities. Leveraging recent foundation models, we first introduce a multi-modal mechanism to integrate open-vocabulary semantic knowledge for effective 2D-3D object matching. Additionally, we design object-oriented reference frames as position priors, paired with a reference frame selection strategy based on the Distance-IoU (DIOU), enabling extension to scalable scenes. Moreover, to ensure stable and accurate pose optimization, we also propose a dual-path 2D Iterative Closest Pixel loss guided by object shape. Experimental results demonstrate that OpenReLoc achieves superior relocalization recall and accuracy across various datasets. Our source code will be released upon acceptance.

Abstract

Relative Pose Estimation

Explore similar work

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization

L3L^3L3:Scene-agnostic Visual Localization in the Wild

VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graph

$L^3$ :Scene-agnostic Visual Localization in the Wild