Query Quantized Neural SLAM

• URL: http://arxiv.org/abs/2412.16476v1
• Date: Sat, 21 Dec 2024 04:08:18 GMT
• Title: Query Quantized Neural SLAM
• Authors: Sijia Jiang, Jing Hua, Zhizhong Han,
• Abstract summary: We propose query quantized neural SLAM to reduce variations of input for easier and faster overfitting a frame. We report visual and numerical comparisons on widely used benchmarks to show our superiority over the latest methods in both reconstruction and camera tracking.
• Score: 25.72309707436261
• License:
• Abstract: Neural implicit representations have shown remarkable abilities in jointly modeling geometry, color, and camera poses in simultaneous localization and mapping (SLAM). Current methods use coordinates, positional encodings, or other geometry features as input to query neural implicit functions for signed distances and color which produce rendering errors to drive the optimization in overfitting image observations. However, due to the run time efficiency requirement in SLAM systems, we are merely allowed to conduct optimization on each frame in few iterations, which is far from enough for neural networks to overfit these queries. The underfitting usually results in severe drifts in camera tracking and artifacts in reconstruction. To resolve this issue, we propose query quantized neural SLAM which uses quantized queries to reduce variations of input for much easier and faster overfitting a frame. To this end, we quantize a query into a discrete representation with a set of codes, and only allow neural networks to observe a finite number of variations. This allows neural networks to become increasingly familiar with these codes after overfitting more and more previous frames. Moreover, we also introduce novel initialization, losses, and argumentation to stabilize the optimization with significant uncertainty in the early optimization stage, constrain the optimization space, and estimate camera poses more accurately. We justify the effectiveness of each design and report visual and numerical comparisons on widely used benchmarks to show our superiority over the latest methods in both reconstruction and camera tracking.

Related papers

• Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images [65.41966114373373]
  We present an improved solution to the neural image-based rendering problem in computer vision. The proposed approach could synthesize a realistic image of the scene from a novel viewpoint at test time.
  arXiv  Detail & Related papers  (2023-11-08T08:18:23Z)
• Training and Predicting Visual Error for Real-Time Applications [6.687091041822445]
  We explore the abilities of convolutional neural networks to predict a variety of visual metrics without requiring either reference or rendered images. Our solution combines image-space information that is readily available in most state-of-the-art deferred shading pipelines with reprojection from previous frames to enable an adequate estimate of visual errors.
  arXiv  Detail & Related papers  (2023-10-13T14:14:00Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• BID-NeRF: RGB-D image pose estimation with inverted Neural Radiance Fields [0.0]
  We aim to improve the Inverted Neural Radiance Fields (iNeRF) algorithm which defines the image pose estimation problem as a NeRF based iterative linear optimization. NeRFs are novel neural space representation models that can synthesize photorealistic novel views of real-world scenes or objects.
  arXiv  Detail & Related papers  (2023-10-05T14:27:06Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• FMapping: Factorized Efficient Neural Field Mapping for Real-Time Dense RGB SLAM [3.6985351289638957]
  We introduce FMapping, an efficient neural field mapping framework that facilitates the continuous estimation of a colorized point cloud map in real-time dense RGB SLAM. We propose an effective factorization scheme for scene representation and introduce a sliding window strategy to reduce the uncertainty for scene reconstruction.
  arXiv  Detail & Related papers  (2023-06-01T11:51:46Z)
• ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization [71.91942002659795]
  We investigate and adapt network quantization techniques to accelerate inference and enable its use on compute limited platforms. ZippyPoint, our efficient quantized network with binary descriptors, improves the network runtime speed, the descriptor matching speed, and the 3D model size. These improvements come at a minor performance degradation as evaluated on the tasks of homography estimation, visual localization, and map-free visual relocalization.
  arXiv  Detail & Related papers  (2022-03-07T18:59:03Z)
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo [97.07453889070574]
  We present a new multi-view depth estimation method that utilizes both conventional SfM reconstruction and learning-based priors. We show that our proposed framework significantly outperforms state-of-the-art methods on indoor scenes.
  arXiv  Detail & Related papers  (2021-09-02T17:54:31Z)
• A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding [57.1077544780653]
  We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems. We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions. This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end.
  arXiv  Detail & Related papers  (2020-06-26T08:34:54Z)
• u-net CNN based fourier ptychography [5.46367622374939]
  We propose a new retrieval algorithm that is based on convolutional neural networks. Experiments demonstrate that our model achieves better reconstruction results and is more robust under system aberrations.
  arXiv  Detail & Related papers  (2020-03-16T22:48:44Z)

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.