Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals

• URL: http://arxiv.org/abs/2503.20066v1
• Date: Tue, 25 Mar 2025 21:01:05 GMT
• Title: Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals
• Authors: Zhirui Dai, Hojoon Shin, Yulun Tian, Ki Myung Brian Lee, Nikolay Atanasov,
• Abstract summary: Recent work shows that implicit continuous representations of occupancy, signed distance, or radiance learned using neural networks offer advantages in reconstruction fidelity, efficiency, and differentiability.<n>In this work, we explore a directional formulation of signed distance, called signed directional distance function (SDDF)<n>We show that SDDF is competitive with the state-of-the-art neural implicit scene models in terms of reconstruction accuracy and rendering efficiency.
• Score: 17.51160139116379
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dense geometric environment representations are critical for autonomous mobile robot navigation and exploration. Recent work shows that implicit continuous representations of occupancy, signed distance, or radiance learned using neural networks offer advantages in reconstruction fidelity, efficiency, and differentiability over explicit discrete representations based on meshes, point clouds, and voxels. In this work, we explore a directional formulation of signed distance, called signed directional distance function (SDDF). Unlike signed distance function (SDF) and similar to neural radiance fields (NeRF), SDDF has a position and viewing direction as input. Like SDF and unlike NeRF, SDDF directly provides distance to the observed surface along the direction, rather than integrating along the view ray, allowing efficient view synthesis. To learn and predict scene-level SDDF efficiently, we develop a differentiable hybrid representation that combines explicit ellipsoid priors and implicit neural residuals. This approach allows the model to effectively handle large distance discontinuities around obstacle boundaries while preserving the ability for dense high-fidelity prediction. We show that SDDF is competitive with the state-of-the-art neural implicit scene models in terms of reconstruction accuracy and rendering efficiency, while allowing differentiable view prediction for robot trajectory optimization.

Related papers

• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Unsupervised Occupancy Learning from Sparse Point Cloud [8.732260277121547]
  Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities. In this paper, we propose a method to infer occupancy fields instead of Neural Signed Distance Functions. We highlight its capacity to improve implicit shape inference with respect to baselines and the state-of-the-art using synthetic and real data.
  arXiv  Detail & Related papers  (2024-04-03T14:05:39Z)
• DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling [0.20287200280084108]
  We learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions. Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance.
  arXiv  Detail & Related papers  (2024-02-14T00:42:19Z)
• Generative Modeling with Phase Stochastic Bridges [49.4474628881673]
  Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. We introduce a novel generative modeling framework grounded in textbfphase space dynamics Our framework demonstrates the capability to generate realistic data points at an early stage of dynamics propagation.
  arXiv  Detail & Related papers  (2023-10-11T18:38:28Z)
• Efficient Parametric Approximations of Neural Network Function Space Distance [6.117371161379209]
  It is often useful to compactly summarize important properties of model parameters and training data so that they can be used later without storing and/or iterating over the entire dataset. We consider estimating the Function Space Distance (FSD) over a training set, i.e. the average discrepancy between the outputs of two neural networks. We propose a Linearized Activation TRick (LAFTR) and derive an efficient approximation to FSD for ReLU neural networks.
  arXiv  Detail & Related papers  (2023-02-07T15:09:23Z)
• CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization [54.69408516025872]
  CAP-UDF is a novel method to learn consistency-aware UDF from raw point clouds. We train a neural network to gradually infer the relationship between queries and the approximated surface. We also introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF.
  arXiv  Detail & Related papers  (2022-10-06T08:51:08Z)
• iSDF: Real-Time Neural Signed Distance Fields for Robot Perception [64.80458128766254]
  iSDF is a continuous learning system for real-time signed distance field reconstruction. It produces more accurate reconstructions and better approximations of collision costs and gradients.
  arXiv  Detail & Related papers  (2022-04-05T15:48:39Z)
• A Deep Signed Directional Distance Function for Object Shape Representation [12.741811850885309]
  This paper develops a new shape model that allows novel distance views by optimizing a continuous signed directional distance function (SDDF) Unlike an SDF, which measures distance to the nearest surface in any direction, an SDDF measures distance in a given direction. Our model encodes by construction the property that SDDF values decrease linearly along the viewing direction.
  arXiv  Detail & Related papers  (2021-07-23T04:11:59Z)
• Domain Adaptive Robotic Gesture Recognition with Unsupervised Kinematic-Visual Data Alignment [60.31418655784291]
  We propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i.e., both kinematic and visual data, from simulator to real robot. It remedies the domain gap with enhanced transferable features by using temporal cues in videos, and inherent correlations in multi-modal towards recognizing gesture. Results show that our approach recovers the performance with great improvement gains, up to 12.91% in ACC and 20.16% in F1score without using any annotations in real robot.
  arXiv  Detail & Related papers  (2021-03-06T09:10:03Z)
• Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces [68.12457459590921]
  Reconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. We introduce textitNeural-Pull, a new approach that is simple and leads to high quality SDFs.
  arXiv  Detail & Related papers  (2020-11-26T23:18:10Z)
• Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance [95.86944752753564]
  We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties. Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates. The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
  arXiv  Detail & Related papers  (2020-07-28T07:34:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.