Z3D: Zero-Shot 3D Visual Grounding from Images

3D visual grounding (3DVG) aims to localize objects in a 3D scene based on natural language queries. In this work, we explore zero-shot 3DVG from multi-view images alone, without requiring any geometric supervision or object priors. We introduce Z3D, a universal grounding pipeline that flexibly operates on multi-view images while optionally incorporating camera poses and depth maps. We identify key bottlenecks in prior zero-shot methods causing significant performance degradation and address them with (i) a state-of-the-art zero-shot 3D instance segmentation method to generate high-quality 3D bounding box proposals and (ii) advanced reasoning via prompt-based segmentation, which utilizes full capabilities of modern VLMs. Extensive experiments on the ScanRefer and Nr3D benchmarks demonstrate that our approach achieves state-of-the-art performance among zero-shot methods. Code is available at https://github.com/col14m/z3d .

Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting

3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our approach explicitly models object instances. It first propagates instance masks across views using depth, thus producing view-consistent 2D masks. Each object is then reconstructed independently and merged back into the scene while refining its boundaries. Finally, instance-level semantic descriptors are embedded in the reconstructed objects, supporting various applications, including panoptic segmentation, object retrieval, and 3D editing. Unlike existing methods, Split&Splat tackles the problem by first segmenting the scene and then reconstructing each object individually. This design naturally supports downstream tasks and allows Split&Splat to achieve state-of-the-art performance on the ScanNetv2 segmentation benchmark.

Instance-Guided Unsupervised Domain Adaptation for Robotic Semantic Segmentation

Semantic segmentation networks, which are essential for robotic perception, often suffer from performance degradation when the visual distribution of the deployment environment differs from that of the source dataset on which they were trained. Unsupervised Domain Adaptation (UDA) addresses this challenge by adapting the network to the robot's target environment without external supervision, leveraging the large amounts of data a robot might naturally collect during long-term operation. In such settings, UDA methods can exploit multi-view consistency across the environment's map to fine-tune the model in an unsupervised fashion and mitigate domain shift. However, these approaches remain sensitive to cross-view instance-level inconsistencies. In this work, we propose a method that starts from a volumetric 3D map to generate multi-view consistent pseudo-labels. We then refine these labels using the zero-shot instance segmentation capabilities of a foundation model, enforcing instance-level coherence. The refined annotations serve as supervision for self-supervised fine-tuning, enabling the robot to adapt its perception system at deployment time. Experiments on real-world data demonstrate that our approach consistently improves performance over state-of-the-art UDA baselines based on multi-view consistency, without requiring any ground-truth labels in the target domain.

From Implicit Ambiguity to Explicit Solidity: Diagnosing Interior Geometric Degradation in Neural Radiance Fields for Dense 3D Scene Understanding

Neural Radiance Fields (NeRFs) have emerged as a powerful paradigm for multi-view reconstruction, complementing classical photogrammetric pipelines based on Structure-from-Motion (SfM) and Multi-View Stereo (MVS). However, their reliability for quantitative 3D analysis in dense, self-occluding scenes remains poorly understood. In this study, we identify a fundamental failure mode of implicit density fields under heavy occlusion, which we term Interior Geometric Degradation (IGD). We show that transmittance-based volumetric optimization satisfies photometric supervision by reconstructing hollow or fragmented structures rather than solid interiors, leading to systematic instance undercounting. Through controlled experiments on synthetic datasets with increasing occlusion, we demonstrate that state-of-the-art mask-supervised NeRFs saturate at approximately 89% instance recovery in dense scenes, despite improved surface coherence and mask quality. To overcome this limitation, we introduce an explicit geometric pipeline based on Sparse Voxel Rasterization (SVRaster), initialized from SfM feature geometry. By projecting 2D instance masks onto an explicit voxel grid and enforcing geometric separation via recursive splitting, our approach preserves physical solidity and achieves a 95.8% recovery rate in dense clusters. A sensitivity analysis using degraded segmentation masks further shows that explicit SfM-based geometry is substantially more robust to supervision failure, recovering 43% more instances than implicit baselines. These results demonstrate that explicit geometric priors are a prerequisite for reliable quantitative analysis in highly self-occluding 3D scenes.

Instance-Guided Radar Depth Estimation for 3D Object Detection

Accurate depth estimation is fundamental to 3D perception in autonomous driving, supporting tasks such as detection, tracking, and motion planning. However, monocular camera-based 3D detection suffers from depth ambiguity and reduced robustness under challenging conditions. Radar provides complementary advantages such as resilience to poor lighting and adverse weather, but its sparsity and low resolution limit its direct use in detection frameworks. This motivates the need for effective Radar-camera fusion with improved preprocessing and depth estimation strategies. We propose an end-to-end framework that enhances monocular 3D object detection through two key components. First, we introduce InstaRadar, an instance segmentation-guided expansion method that leverages pre-trained segmentation masks to enhance Radar density and semantic alignment, producing a more structured representation. InstaRadar achieves state-of-the-art results in Radar-guided depth estimation, showing its effectiveness in generating high-quality depth features. Second, we integrate the pre-trained RCDPT into the BEVDepth framework as a replacement for its depth module. With InstaRadar-enhanced inputs, the RCDPT integration consistently improves 3D detection performance. Overall, these components yield steady gains over the baseline BEVDepth model, demonstrating the effectiveness of InstaRadar and the advantage of explicit depth supervision in 3D object detection. Although the framework lags behind Radar-camera fusion models that directly extract BEV features, since Radar serves only as guidance rather than an independent feature stream, this limitation highlights potential for improvement. Future work will extend InstaRadar to point cloud-like representations and integrate a dedicated Radar branch with temporal cues for enhanced BEV fusion.

3AM: 3egment Anything with Geometric Consistency in Videos

Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods address viewpoint consistency but require camera poses, depth maps, and expensive preprocessing. We introduce 3AM, a training-time enhancement that integrates 3D-aware features from MUSt3R into SAM2. Our lightweight Feature Merger fuses multi-level MUSt3R features that encode implicit geometric correspondence. Combined with SAM2's appearance features, the model achieves geometry-consistent recognition grounded in both spatial position and visual similarity. We propose a field-of-view aware sampling strategy ensuring frames observe spatially consistent object regions for reliable 3D correspondence learning. Critically, our method requires only RGB input at inference, with no camera poses or preprocessing. On challenging datasets with wide-baseline motion (ScanNet++, Replica), 3AM substantially outperforms SAM2 and extensions, achieving 90.6% IoU and 71.7% Positive IoU on ScanNet++'s Selected Subset, improving over state-of-the-art VOS methods by +15.9 and +30.4 points. Project page: https://jayisaking.github.io/3AM-Page/

ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes

Indoor environments evolve as objects move, appear, or disappear. Capturing these dynamics requires maintaining temporally consistent instance identities across intermittently captured 3D scans, even when changes are unobserved. We introduce and formalize the task of temporally sparse 4D indoor semantic instance segmentation (SIS), which jointly segments, identifies, and temporally associates object instances. This setting poses a challenge for existing 3DSIS methods, which require a discrete matching step due to their lack of temporal reasoning, and for 4D LiDAR approaches, which perform poorly due to their reliance on high-frequency temporal measurements that are uncommon in the longer-horizon evolution of indoor environments. We propose ReScene4D, a novel method that adapts 3DSIS architectures for 4DSIS without needing dense observations. It explores strategies to share information across observations, demonstrating that this shared context not only enables consistent instance tracking but also improves standard 3DSIS quality. To evaluate this task, we define a new metric, t-mAP, that extends mAP to reward temporal identity consistency. ReScene4D achieves state-of-the-art performance on the 3RScan dataset, establishing a new benchmark for understanding evolving indoor scenes.

DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integration

Perception is a cornerstone of autonomous driving, enabling vehicles to understand their surroundings and make safe, reliable decisions. Developing robust perception algorithms requires large-scale, high-quality datasets that cover diverse driving conditions and support thorough evaluation. Existing datasets often lack a high-fidelity digital twin, limiting systematic testing, edge-case simulation, sensor modification, and sim-to-real evaluations. To address this gap, we present DrivIng, a large-scale multimodal dataset with a complete geo-referenced digital twin of a ~18 km route spanning urban, suburban, and highway segments. Our dataset provides continuous recordings from six RGB cameras, one LiDAR, and high-precision ADMA-based localization, captured across day, dusk, and night. All sequences are annotated at 10 Hz with 3D bounding boxes and track IDs across 12 classes, yielding ~1.2 million annotated instances. Alongside the benefits of a digital twin, DrivIng enables a 1-to-1 transfer of real traffic into simulation, preserving agent interactions while enabling realistic and flexible scenario testing. To support reproducible research and robust validation, we benchmark DrivIng with state-of-the-art perception models and publicly release the dataset, digital twin, HD map, and codebase.

High-Fidelity 3D Tooth Reconstruction by Fusing Intraoral Scans and CBCT Data via a Deep Implicit Representation

High-fidelity 3D tooth models are essential for digital dentistry, but must capture both the detailed crown and the complete root. Clinical imaging modalities are limited: Cone-Beam Computed Tomography (CBCT) captures the root but has a noisy, low-resolution crown, while Intraoral Scanners (IOS) provide a high-fidelity crown but no root information. A naive fusion of these sources results in unnatural seams and artifacts. We propose a novel, fully-automated pipeline that fuses CBCT and IOS data using a deep implicit representation. Our method first segments and robustly registers the tooth instances, then creates a hybrid proxy mesh combining the IOS crown and the CBCT root. The core of our approach is to use this noisy proxy to guide a class-specific DeepSDF network. This optimization process projects the input onto a learned manifold of ideal tooth shapes, generating a seamless, watertight, and anatomically coherent model. Qualitative and quantitative evaluations show our method uniquely preserves both the high-fidelity crown from IOS and the patient-specific root morphology from CBCT, overcoming the limitations of each modality and naive stitching.

Active Cross-Modal Visuo-Tactile Perception of Deformable Linear Objects

This paper presents a novel cross-modal visuo-tactile perception framework for the 3D shape reconstruction of deformable linear objects (DLOs), with a specific focus on cables subject to severe visual occlusions. Unlike existing methods relying predominantly on vision, whose performance degrades under varying illumination, background clutter, or partial visibility, the proposed approach integrates foundation-model-based visual perception with adaptive tactile exploration. The visual pipeline exploits SAM for instance segmentation and Florence for semantic refinement, followed by skeletonization, endpoint detection, and point-cloud extraction. Occluded cable segments are autonomously identified and explored with a tactile sensor, which provides local point clouds that are merged with the visual data through Euclidean clustering and topology-preserving fusion. A B-spline interpolation driven by endpoint-guided point sorting yields a smooth and complete reconstruction of the cable shape. Experimental validation using a robotic manipulator equipped with an RGB-D camera and a tactile pad demonstrates that the proposed framework accurately reconstructs both simple and highly curved single or multiple cable configurations, even when large portions are occluded. These results highlight the potential of foundation-model-enhanced cross-modal perception for advancing robotic manipulation of deformable objects.