PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

• URL: http://arxiv.org/abs/2606.03989v1
• Date: Tue, 02 Jun 2026 17:59:22 GMT
• Title: PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation
• Abstract summary: We envision pixels synthesizing higher-level signals locally, reducing downstream load, and providing richer inputs for higher-level vision tasks.<n>We propose a fully parallelizable form of visual odometry and depth estimation across pixels.<n>Our method is evaluated on realistic datasets, demonstrating the feasibility of GBP-based pixel-level distributed odometry and depth estimation.
• Score: 28.375541390903603
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Images composed of 2D pixel arrays are the standard input to computer vision algorithms, yet many underlying computations can be distributed across pixels. Transmitting raw, redundant, and noisy pixel data off the sensor remains inefficient, motivating a shift toward focal-plane sensor-processors that perform a significant part of the computation directly within each pixel. We envision pixels synthesizing higher-level signals locally, reducing downstream load, and providing richer inputs for higher-level vision tasks. We propose a fully parallelizable form of visual odometry and depth estimation across pixels, where sensor-processors exchange information through Gaussian Belief Propagation (GBP) to achieve consensus about camera motion and infer depth from per-pixel photometric observations and a surface normal prior. To maintain geometric stability during optimization, we introduce a keyframe-like anchoring mechanism that regulates the effective baseline between frames, enabling consistent motion and depth updates. Our method is evaluated on realistic datasets, demonstrating the feasibility of GBP-based pixel-level distributed odometry and depth estimation with keyframe anchoring on-sensor. Project Page: https://www.shinjeongkim.com/pixvod/

Related papers

• Square Superpixel Generation and Representation Learning via Granular Ball Computing [97.99956628286243]
  Superpixels provide a compact region-based representation that preserves object boundaries and local structures.<n>Most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions.<n>Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach.
  arXiv  Detail & Related papers  (2026-03-31T09:06:58Z)
• FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers [91.59069344768858]
  We introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder.<n>FreqPDE combines the 2D image features and 3D position embeddings to generate 3D depth-aware features for query decoding.
  arXiv  Detail & Related papers  (2025-10-17T07:36:54Z)
• Leveraging Motion Estimation for Efficient Bayer-Domain Computer Vision [12.940116042097847]
  Existing computer vision processing pipeline acquires visual information using an image sensor that captures pixel information in the Bayer pattern.<n>The raw sensor data are then processed using an image signal processor (ISP) that first converts Bayer pixel data to RGB on a pixel by pixel basis, followed by video convolutional network (VCN) processing on a frame by frame basis.<n>We propose a novel framework that eliminates the ISP and leverages motion estimation to accelerate video vision tasks directly in the Bayer domain.
  arXiv  Detail & Related papers  (2025-01-25T08:09:54Z)
• Data-Driven Pixel Control: Challenges and Prospects [13.158333009169418]
  We study a data-driven system that combines dynamic sensing at the pixel level with computer vision analytics at the video level. Our system achieves a 10X reduction in bandwidth and a 15-30X improvement in Energy-Delay Product (EDP) when activating only 30% of pixels.
  arXiv  Detail & Related papers  (2024-08-08T21:49:19Z)
• PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation [12.942063363292888]
  We propose a novel photometric rotation estimation algorithm to be distributed at pixel level.<n>Each pixel estimates the global motion of the camera by exchanging information with other pixels to achieve global consensus.
  arXiv  Detail & Related papers  (2024-06-14T05:28:45Z)
• Parameter-Inverted Image Pyramid Networks [49.35689698870247]
  We propose a novel network architecture known as the Inverted Image Pyramid Networks (PIIP) Our core idea is to use models with different parameter sizes to process different resolution levels of the image pyramid. PIIP achieves superior performance in tasks such as object detection, segmentation, and image classification.
  arXiv  Detail & Related papers  (2024-06-06T17:59:10Z)
• Pixel-Inconsistency Modeling for Image Manipulation Localization [59.968362815126326]
  Digital image forensics plays a crucial role in image authentication and manipulation localization. This paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts. Experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints.
  arXiv  Detail & Related papers  (2023-09-30T02:54:51Z)
• Probabilistic Deep Metric Learning for Hyperspectral Image Classification [91.5747859691553]
  This paper proposes a probabilistic deep metric learning framework for hyperspectral image classification. It aims to predict the category of each pixel for an image captured by hyperspectral sensors. Our framework can be readily applied to existing hyperspectral image classification methods.
  arXiv  Detail & Related papers  (2022-11-15T17:57:12Z)
• A photosensor employing data-driven binning for ultrafast image recognition [0.0]
  Pixel binning is a technique widely used in optical image acquisition and spectroscopy. Here, we push the concept of binning to its limit by combining a large fraction of the sensor elements into a single superpixel. For a given pattern recognition task, its optimal shape is determined from training data using a machine learning algorithm.
  arXiv  Detail & Related papers  (2021-11-20T15:38:39Z)
• Pixel-Perfect Structure-from-Motion with Featuremetric Refinement [96.73365545609191]
  We refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.
  arXiv  Detail & Related papers  (2021-08-18T17:58:55Z)
• Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays [16.531637803429277]
  We present a novel method of CNN inference for pixel processor array ( PPA) vision sensors. Our approach can perform convolutional layers, max pooling, ReLu, and a final fully connected layer entirely upon the PPA sensor. This is the first work demonstrating CNN inference conducted entirely upon the processor array of a PPA vision sensor device, requiring no external processing.
  arXiv  Detail & Related papers  (2020-04-27T01:00:35Z)

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.