@inproceedings{bib_SILI_2026, AUTHOR = {R, Tarun and Verma, Anuj and Nanwani, Laksh and GARG, SOURAV and Krishna, K Madhava }, TITLE = {SILICA: Repurposing Diffusion Priors for Joint Glass Segmentation and Depth Estimation}, BOOKTITLE = {International Conference on Intelligent Robots and Systems}. YEAR = {2026}}

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.

@inproceedings{bib_SegC_2026, AUTHOR = {Prakash, Punnavajhala Gnana and Tourani, Satyajit and TOURANI, SIDDHARTH and Krishna, K Madhava and GARG, SOURAV and Khan, Muhammad Haris }, TITLE = {SegCapVPR: Leveraging Segment Captioning for Visual Place Recognition}, BOOKTITLE = {Workshop on Computer Vision in the Wild}. YEAR = {2026}}

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.

@inproceedings{bib_Pixe_2026, AUTHOR = {Chittawar, Sarthak and Garg, Vansh and Vadali, Aditya Subbaraya Sri Chandramouli and Manojbhai, Pandya Krish and Sreekanth, Jayanti Rohit and GARG, SOURAV and Krishna, K Madhava }, TITLE = {PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops}, BOOKTITLE = {International Conference on Intelligent Robots and Systems}. YEAR = {2026}}

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.

@inproceedings{bib_MASt_2026, AUTHOR = {Garg, Vansh and Sreekanth, Jayanti Rohit and Manojbhai, Pandya Krish and Chittawar, Sarthak and TOURANI, SIDDHARTH and Khan, Muhammad Haris and GARG, SOURAV and Krishna, K Madhava }, TITLE = {MASt3R-Nav: WayPixel Navigation in Relative 3D Maps}, BOOKTITLE = {International Conference on Robotics and Automation}. YEAR = {2026}}

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.