From Single Images to Motion Policies via Video-Generation Environment Representations

Autonomous robots typically need to construct representations of their surroundings and adapt their motions to the geometry of their environment. Here, we tackle the problem of constructing a policy model for collision-free motion generation, consistent with the environment, from a single input RGB image. Extracting 3D structures from a single image often involves monocular depth estimation. Developments in depth estimation have given rise to large pre-trained models such as DepthAnything. However, using outputs of these models for downstream motion generation is challenging due to frustum-shaped errors that arise. Instead, we propose a framework known as Video-Generation Environment Representation (VGER), which leverages the advances of large-scale video generation models to generate a moving camera video conditioned on the input image. Frames of this video, which form a multiview dataset, are then input into a pre-trained 3D foundation model to produce a dense point cloud. We then introduce a multi-scale noise approach to train an implicit representation of the environment structure and build a motion generation model that complies with the geometry of the representation. We extensively evaluate VGER over a diverse set of indoor and outdoor environments. We demonstrate its ability to produce smooth motions that account for the captured geometry of a scene, all from a single RGB input image.

Spatial RoboGrasp: Generalized Robotic Grasping Control Policy

Achieving generalizable and precise robotic manipulation across diverse environments remains a critical challenge, largely due to limitations in spatial perception. While prior imitation-learning approaches have made progress, their reliance on raw RGB inputs and handcrafted features often leads to overfitting and poor 3D reasoning under varied lighting, occlusion, and object conditions. In this paper, we propose a unified framework that couples robust multimodal perception with reliable grasp prediction. Our architecture fuses domain-randomized augmentation, monocular depth estimation, and a depth-aware 6-DoF Grasp Prompt into a single spatial representation for downstream action planning. Conditioned on this encoding and a high-level task prompt, our diffusion-based policy yields precise action sequences, achieving up to 40% improvement in grasp success and 45% higher task success rates under environmental variation. These results demonstrate that spatially grounded perception, paired with diffusion-based imitation learning, offers a scalable and robust solution for general-purpose robotic grasping.

4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians

We propose the first 4D tracking and mapping method that jointly performs camera localization and non-rigid surface reconstruction via differentiable rendering. Our approach captures 4D scenes from an online stream of color images with depth measurements or predictions by jointly optimizing scene geometry, appearance, dynamics, and camera ego-motion. Although natural environments exhibit complex non-rigid motions, 4D-SLAM remains relatively underexplored due to its inherent challenges; even with 2.5D signals, the problem is ill-posed because of the high dimensionality of the optimization space. To overcome these challenges, we first introduce a SLAM method based on Gaussian surface primitives that leverages depth signals more effectively than 3D Gaussians, thereby achieving accurate surface reconstruction. To further model non-rigid deformations, we employ a warp-field represented by a multi-layer perceptron (MLP) and introduce a novel camera pose estimation technique along with surface regularization terms that facilitate spatio-temporal reconstruction. In addition to these algorithmic challenges, a significant hurdle in 4D SLAM research is the lack of reliable ground truth and evaluation protocols, primarily due to the difficulty of 4D capture using commodity sensors. To address this, we present a novel open synthetic dataset of everyday objects with diverse motions, leveraging large-scale object models and animation modeling. In summary, we open up the modern 4D-SLAM research by introducing a novel method and evaluation protocols grounded in modern vision and rendering techniques.

Joint Depth and Reflectivity Estimation using Single-Photon LiDAR

Single-Photon Light Detection and Ranging (SP-LiDAR is emerging as a leading technology for long-range, high-precision 3D vision tasks. In SP-LiDAR, timestamps encode two complementary pieces of information: pulse travel time (depth) and the number of photons reflected by the object (reflectivity). Existing SP-LiDAR reconstruction methods typically recover depth and reflectivity separately or sequentially use one modality to estimate the other. Moreover, the conventional 3D histogram construction is effective mainly for slow-moving or stationary scenes. In dynamic scenes, however, it is more efficient and effective to directly process the timestamps. In this paper, we introduce an estimation method to simultaneously recover both depth and reflectivity in fast-moving scenes. We offer two contributions: (1) A theoretical analysis demonstrating the mutual correlation between depth and reflectivity and the conditions under which joint estimation becomes beneficial. (2) A novel reconstruction method, "SPLiDER", which exploits the shared information to enhance signal recovery. On both synthetic and real SP-LiDAR data, our method outperforms existing approaches, achieving superior joint reconstruction quality.

Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss

Novel view synthesis is a fundamental task in 3D computer vision that aims to reconstruct realistic images from a set of posed input views. However, reconstruction quality degrades significantly under sparse-view conditions due to limited geometric cues. Existing methods, such as Neural Radiance Fields (NeRF) and the more recent 3D Gaussian Splatting (3DGS), often suffer from blurred details and structural artifacts when trained with insufficient views. Recent works have identified the quality of rendered depth as a key factor in mitigating these artifacts, as it directly affects geometric accuracy and view consistency. In this paper, we address these challenges by introducing Hierarchical Depth-Guided Splatting (HDGS), a depth supervision framework that progressively refines geometry from coarse to fine levels. Central to HDGS is a novel Cascade Pearson Correlation Loss (CPCL), which aligns rendered and estimated monocular depths across multiple spatial scales. By enforcing multi-scale depth consistency, our method substantially improves structural fidelity in sparse-view scenarios. Extensive experiments on the LLFF and DTU benchmarks demonstrate that HDGS achieves state-of-the-art performance under sparse-view settings while maintaining efficient and high-quality rendering

A Shape-Aware Total Body Photography System for In-focus Surface Coverage Optimization

Total Body Photography (TBP) is becoming a useful screening tool for patients at high risk for skin cancer. While much progress has been made, existing TBP systems can be further improved for automatic detection and analysis of suspicious skin lesions, which is in part related to the resolution and sharpness of acquired images. This paper proposes a novel shape-aware TBP system automatically capturing full-body images while optimizing image quality in terms of resolution and sharpness over the body surface. The system uses depth and RGB cameras mounted on a 360-degree rotary beam, along with 3D body shape estimation and an in-focus surface optimization method to select the optimal focus distance for each camera pose. This allows for optimizing the focused coverage over the complex 3D geometry of the human body given the calibrated camera poses. We evaluate the effectiveness of the system in capturing high-fidelity body images. The proposed system achieves an average resolution of 0.068 mm/pixel and 0.0566 mm/pixel with approximately 85% and 95% of surface area in-focus, evaluated on simulation data of diverse body shapes and poses as well as a real scan of a mannequin respectively. Furthermore, the proposed shape-aware focus method outperforms existing focus protocols (e.g. auto-focus). We believe the high-fidelity imaging enabled by the proposed system will improve automated skin lesion analysis for skin cancer screening.

Empirical 3D Channel Modeling for Cellular-Connected UAVs: A Triple-Layer Machine Learning Approach

This work proposes an empirical air to ground (A2G) propagation model specifically designed for cellular connected unmanned aerial vehicles (UAVs). An in depth aerial drive test was carried out within an operating Long Term Evolution (LTE) network, gathering thorough measurements of key network parameters. Rigid preprocessing and statistical analysis of these data produced a strong foundation for training a new triple layer machine learning (ML) model. The proposed ML framework employs a systematic hierarchical approach. Accordingly, the first two layers, Stepwise Linear Regression (STW) and Ensemble of Bagged Trees (EBT) generate predictions independently, meanwhile, the third layer, Gaussian Process Regression (GPR), explicitly acts as an aggregation layer, refining these predictions to accurately estimate Key Performance Indicators (KPIs) such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength (RSSI), and Path Loss (PL). Compared to traditional single layer ML or computationally intensive ray tracing approaches, the proposed triple layer ML framework significantly improves predictive accuracy and robustness, achieving around 99 percent accuracy in training and above 90 percent in testing while utilizing a minimal but effective feature set log transformed 3D and 2D propagation distances, azimuth, and elevation angles. This streamlined feature selection substantially reduces computing complexity, thus enhancing scalability across various operating environments. The proposed frameworks practicality and efficacy for real world deployment in UAV integrated cellular networks are further demonstrated by comparative analyses, which underscore its substantial improvement.

3D Reconstruction from Sketches

We consider the problem of reconstructing a 3D scene from multiple sketches. We propose a pipeline which involves (1) stitching together multiple sketches through use of correspondence points, (2) converting the stitched sketch into a realistic image using a CycleGAN, and (3) estimating that image's depth-map using a pre-trained convolutional neural network based architecture called MegaDepth. Our contribution includes constructing a dataset of image-sketch pairs, the images for which are from the Zurich Building Database, and sketches have been generated by us. We use this dataset to train a CycleGAN for our pipeline's second step. We end up with a stitching process that does not generalize well to real drawings, but the rest of the pipeline that creates a 3D reconstruction from a single sketch performs quite well on a wide variety of drawings.

DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection

3D Lane detection plays an important role in autonomous driving. Recent advances primarily build Birds-Eye-View (BEV) feature from front-view (FV) images to perceive 3D information of Lane more effectively. However, constructing accurate BEV information from FV image is limited due to the lacking of depth information, causing previous works often rely heavily on the assumption of a flat ground plane. Leveraging monocular depth estimation to assist in constructing BEV features is less constrained, but existing methods struggle to effectively integrate the two tasks. To address the above issue, in this paper, an accurate 3D lane detection method based on depth-aware BEV feature transtormation is proposed. In detail, an effective feature extraction module is designed, in which a Depth Net is integrated to obtain the vital depth information for 3D perception, thereby simplifying the complexity of view transformation. Subquently a feature reduce module is proposed to reduce height dimension of FV features and depth features, thereby enables effective fusion of crucial FV features and depth features. Then a fusion module is designed to build BEV feature from prime FV feature and depth information. The proposed method performs comparably with state-of-the-art methods on both synthetic Apollo, realistic OpenLane datasets.

SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations

Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-view inputs. We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations, thereby alleviating reconstruction ambiguity. Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency, further reinforced by a unified scale estimation strategy to handle scale discrepancies across datasets. Furthermore, by integrating monocular depth priors with semantic features in the video latent space, our framework directly regresses 3D Gaussian primitives and efficiently processes long-sequence features using a hybrid network structure. Extensive experiments show our method enhances sparse view reconstruction and restores the realistic appearance of 3D scenes.