Abstract

Standard depth sensors systematically fail on transparent surfaces, creating corrupted 3D maps and severe navigation hazards. While specialized hardware sensors can detect glass, they lack modularity and have extensive hardware dependencies. Consequently, learning-based monocular depth estimation has emerged as a compelling alternative. However, domain-specific glass-aware monocular depth estimators struggle with unfamiliar indoor layouts; restricted by the severe scarcity of real-world glass depth annotations, they fail to generalize zero-shot to new settings. This motivates us to explore whether the extensive priors of text-to-image diffusion models can enable generalizable perception of transparent surfaces. We introduce SILICA, a unified pipeline leveraging these priors to jointly predict glass segmentation and glass-aware depth. This mutual information exchange establishes a robust spatial hierarchy, entirely eliminating the need for paired real-world glass depth annotations. Subsequently, we use the predicted segmentation mask to explicitly filter incorrect glass depth points from standard sensors, recovering accurate metric glass depth for downstream 3D mapping and autonomous collision avoidance. Supported by our novel Mirage 18k dataset, extensive experiments demonstrate that SILICA achieves remarkable zero-shot transfer across diverse, unseen environments, outperforming state-of-the-art models by almost 20% and setting a new benchmark for transparent surface perception.

Abstract

Visual Place Recognition (VPR) enables long-term localization by matching query images against a reference database, yet remains vulnerable to severe appearance changes, viewpoint shifts, and perceptual aliasing. We propose SegCapVPR, a unified framework for multimodal and cross-modal VPR that jointly models global scene context, segment-level structure, and aligned linguistic semantics. Our method extracts whole-image and region-level features using DINOv2 and grounds them to segment-specific captions encoded by SigLIP2 through segment-caption alignment on pseudo-labeled data from GSV-Cities and ScanNet. The grounded tokens are aggregated via an optimal transport-based module to produce compact retrieval descriptors. By integrating visual and textual cues at the segment level, SegCapVPR learns semantically enriched and spatially aware representations that improve robustness under challenging conditions. Experiments on indoor and outdoor benchmarks demonstrate substantial gains on Baidu Mall and AmsterTime, while remaining competitive on Pitts30K-Test, and MSLS-Val, establishing a unified paradigm for multimodal (image + text) and cross-modal (text -> image) VPR.

Abstract

Although topological mapping and navigation have been studied extensively, the specific role and downstream effect of loop closures in purely topological representations has received relatively little attention. Importantly, loop closure over topological maps is distinct from loop closure over globally referenced trajectories and metric maps. Building on recent denser topologies grounded in pixel-level, relative 3D geometry, we propose Pixel Loop which introduces loop closures directly in pixel space. Unlike sparse image-level edges or pose-graph corrections in SLAM, our pixel-level closures act as dense topological shortcuts that alter planning connectivity and cost propagation rather than merely aligning coordinates. This dense connectivity enables stable any-point-to-any-point navigation and produces costmaps that align accurately with geometric shortest paths. In particular, we showcase the distinct advantage of applying loop closures to fine-grained pixel topologies rather than image-level topologies. Across extensive simulated experiments, Pixel Loop achieves over 35% absolute improvement in both Success Rate and SPL compared to image-relative baselines, with the largest gains in scenarios requiring shortcut exploitation. Results are further validated through real-world mobile robot deployments, demonstrating that dense pixel-level loop closures provide a practical and robust foundation for topological visual navigation.

Abstract

Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relative topological graphs almost entirely do away with geometric understanding. But, this comes at the cost of navigation capability, often limiting it to merely teach-and-repeat. In this work, we propose a novel map representation in the form of pixel-relative connectivity, which is geometrically accurate but does not require global geometric consistency. Inspired by recent progress in 3D grounded image matching, we construct a map from an image sequence through inter-image connectivity based on pixel correspondences in the relative 3D coordinate systems of individual image pairs. We then use this pixel-level graph to perform global path planning by approximating and sparsifying intra-image pixel connectivity. Through this, we derive a ''WayPixel Costmap'' representation and train a controller conditioned on it to predict a trajectory rollout. We show that this dense pixel-level costmap based on relative geometry is a more accurate conditioning variable for control prediction than its image- and object-level counterparts. This enables a highly capable navigation system, as validated on four types of navigation tasks in the simulator and through real world demonstrations.

Abstract

Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features, segment matching captures structured regions, offering greater robustness to occlusions, lighting variations, and viewpoint changes. In this paper, we leverage the spatial understanding of 3D foundation models to tackle wide-baseline segment matching, a challenging setting involving extreme viewpoint shifts. We propose an architecture that uses the inductive bias of these 3D foundation models to match segments across image pairs with up to 180 degree view-point change rotation. Extensive experiments show that our approach outperforms state-of-the-art methods, including the SAM2 video propagator and local feature matching methods, by up to 30% on the AUPRC metric, on ScanNet++ and Replica datasets. We further demonstrate benefits of the proposed model on relevant downstream tasks, including 3D instance mapping and object-relative navigation.

Project Page: https://segmast3r.github.io/

Abstract

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the whole image and search for matches.
This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap.
We address this by encoding and searching for image segments instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to revisit anything by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place.

Abstract

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While
foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging
scenarios. We introduce DiffPrompter, a novel differentiable
visual and latent prompting mechanism aimed at expanding
the learning capabilities of existing adaptors in foundation
models. Our proposed ∇HFC (High Frequency Components)
based image processing block excels particularly in adverse
weather conditions, where conventional methods often fall
short. Furthermore, we investigate the advantages of jointly
training visual and latent prompts, demonstrating that this
combined approach significantly enhances performance in outof-distribution scenarios. Our differentiable visual prompts
leverage parallel and series architectures to generate prompts,
effectively improving object segmentation tasks in adverse
conditions. Through a comprehensive series of experiments
and evaluations, we provide empirical evidence to support the
efficacy of our approach.

Abstract

Understanding the structural organisation of 3D indoor scenes in terms of rooms is often accomplished via floorplan extraction. Robotic tasks such as planning and navigation require a semantic understanding of the scene as well. This is typically achieved via object-level semantic segmentation. However, such methods struggle to segment out topological regions like "kitchen" in the scene. In this work, we introduce a two-step pipeline. First, we extract a topological map, i.e., floorplan of the indoor scene using a novel multi-channel occupancy representation. Then, we generate CLIP-aligned features and semantic labels for every room instance based on the objects it contains using a self-attention transformer. Our language-topology alignment supports natural language querying, e.g. a "place to cook" locates the "kitchen". We outperform the current state-of-the-art on room segmentation by ∼20% and room classification by ∼12%. Our detailed qualitative analysis and ablation studies provide insights into the problem of joint structural and semantic 3D scene understanding.

Abstract

Visual Place Recognition (VPR) is vital for robot localization. To date, the most performant VPR approaches are environment- and task-specific : while they exhibit strong performance in structured environments (predominantly urban driving), their performance degrades severely in unstructured environments, rendering most approaches brittle to robust real-world deployment. In this work, we develop a universal solution to VPR - a technique that works across a broad range of structured and unstructured environments (urban, outdoors, indoors, aerial, underwater, and subterranean environments) without any re-training or finetuning. We demonstrate that general-purpose feature representations derived from off-the-shelf self-supervised models with no VPR-specific training are the right substrate upon which to build such a universal VPR solution. Combining these derived features with unsupervised feature aggregation enables our suite of methods, AnyLoc , to achieve up to 4× significantly higher performance than existing approaches. We further obtain a 6% improvement in performance by characterizing the semantic properties of these features, uncovering unique domains which encapsulate datasets from similar environments. Our detailed experiments and analysis lay a foundation for building VPR solutions that may be deployed anywhere , anytime , and across anyview . We encourage the readers to explore our project page and interactive demos: https://anyloc.github.io/ .

Abstract

In this paper we present a novel framework for unsupervised topological clustering resulting in improved loop detection and closure for SLAM. A navigating mobile robot clusters its traversal into visually similar topologies where each cluster (topology) contains a set of similar looking images typically observed from spatially adjacent locations. Each such set of spatially adjacent and visually similar grouping of images constitutes a topology obtained without any supervision. We formulate a hierarchical loop discovery strategy that first detects loops at the level of topologies and subsequently at the level of images between the looped topologies. We show over a number of traversals across different Habitat environments that such a hierarchical pipeline significantly improves SOTA image based loop detection and closure methods. Further, as a consequence of improved loop detection, we enhance the loop closure and backend SLAM performance. Such a rendering of a traversal into topological segments is beneficial for downstream tasks such as navigation that can now build a topological graph where spatially adjacent topological clusters are connected by an edge and navigate over such topological graphs.