Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations

• URL: http://arxiv.org/abs/2503.10464v1
• Date: Thu, 13 Mar 2025 15:37:11 GMT
• Title: Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
• Authors: Xunzhi Zheng, Dan Xu,
• Abstract summary: Flow-NeRF is a unified framework that simultaneously optimize scene geometry, camera poses, and dense optical flow all on-the-fly.<n>We develop an effective feature enhancement mechanism to pass canonical space features to world space representations.<n>Our approach surpasses previous methods in almost all metrics for novel-view view synthesis and depth estimation.
• Score: 8.932991182772092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow estimators to derive analytical poses. However, the potential for jointly learning scene geometry, camera poses, and dense flow within a unified neural representation remains largely unexplored. In this paper, we present Flow-NeRF, a unified framework that simultaneously optimizes scene geometry, camera poses, and dense optical flow all on-the-fly. To enable the learning of dense flow within the neural radiance field, we design and build a bijective mapping for flow estimation, conditioned on pose. To make the scene reconstruction benefit from the flow estimation, we develop an effective feature enhancement mechanism to pass canonical space features to world space representations, significantly enhancing scene geometry. We validate our model across four important tasks, i.e., novel view synthesis, depth estimation, camera pose prediction, and dense optical flow estimation, using several datasets. Our approach surpasses previous methods in almost all metrics for novel-view view synthesis and depth estimation and yields both qualitatively sound and quantitatively accurate novel-view flow. Our project page is https://zhengxunzhi.github.io/flownerf/.

Related papers

• NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields [13.178099653374945]
  NeRF-VO integrates learning-based sparse visual odometry for low-latency camera tracking and a neural radiance scene representation. We surpass SOTA methods in pose estimation accuracy, novel view fidelity, and dense reconstruction quality across a variety of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-12-20T22:42:17Z)
• Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow [25.23550076996421]
  We propose to leverage the geometric connection between optical flow estimation and stereo matching. We turn the monocular depth datasets into stereo ones via virtual disparity. We also introduce virtual camera motion into stereo data to produce additional flows along the vertical direction.
  arXiv  Detail & Related papers  (2023-10-03T06:56:07Z)
• Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects [3.794605440322862]
  In this work, we construct a joint inter-frame-supervised depth and optical flow estimation framework. For motion segmentation, we adaptively segment the preliminary estimated optical flow map with large areas of connectivity. Our proposed joint depth and optical flow estimation outperforms existing depth estimators on the KITTI Depth dataset.
  arXiv  Detail & Related papers  (2023-09-07T04:00:52Z)
• DARF: Depth-Aware Generalizable Neural Radiance Field [51.29437249009986]
  We propose the Depth-Aware Generalizable Neural Radiance Field (DARF) with a Depth-Aware Dynamic Sampling (DADS) strategy.<n>Our framework infers the unseen scenes on both pixel level and geometry level with only a few input images.<n>Compared with state-of-the-art generalizable NeRF methods, DARF reduces samples by 50%, while improving rendering quality and depth estimation.
  arXiv  Detail & Related papers  (2022-12-05T14:00:59Z)
• Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving [8.045833295463094]
  We introduce a fully Visual Attention-based Depth (VADepth) network, where spatial attention and channel attention are applied to all stages. By continuously extracting the dependencies of features along the spatial and channel dimensions over a long distance, VADepth network can effectively preserve important details. Experimental results on the KITTI dataset show that this architecture achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-05-18T08:01:38Z)
• Dimensions of Motion: Learning to Predict a Subspace of Optical Flow from a Single Image [50.9686256513627]
  We introduce the problem of predicting, from a single video frame, a low-dimensional subspace of optical flow which includes the actual instantaneous optical flow. We show how several natural scene assumptions allow us to identify an appropriate flow subspace via a set of basis flow fields parameterized by disparity. This provides a new approach to learning these tasks in an unsupervised fashion using monocular input video without requiring camera intrinsics or poses.
  arXiv  Detail & Related papers  (2021-12-02T18:52:54Z)
• Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation [47.984368369734995]
  We introduce a novel recurrent encoding-decoding neural network architecture for event-based optical flow estimation. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2021-09-10T13:37:37Z)
• Optical Flow Estimation from a Single Motion-blurred Image [66.2061278123057]
  Motion blur in an image may have practical interests in fundamental computer vision problems. We propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner.
  arXiv  Detail & Related papers  (2021-03-04T12:45:18Z)
• Neural Topological SLAM for Visual Navigation [112.73876869904]
  We design topological representations for space that leverage semantics and afford approximate geometric reasoning. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation.
  arXiv  Detail & Related papers  (2020-05-25T17:56:29Z)
• Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization [59.9673626329892]
  We exploit the global relationship between optical flow and camera motion using epipolar geometry. We use implicit differentiation to enable back-propagation through the lower-level geometric optimization layer independent of its implementation.
  arXiv  Detail & Related papers  (2020-02-26T22:28:00Z)

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.