On the Global Photometric Alignment for Low-Level Vision

• URL: http://arxiv.org/abs/2604.08172v1
• Date: Thu, 09 Apr 2026 12:29:54 GMT
• Title: On the Global Photometric Alignment for Low-Level Vision
• Abstract summary: Supervised low-level vision models rely on pixel-wise losses against paired references, yet paired training sets exhibit per-pair photometric inconsistency.<n>Standard reconstruction losses allocate disproportionate gradient budget to conflicting per-pair photometric targets, crowding out content restoration.<n>Motivated by this analysis, we propose Photometric Alignment Loss (PAL)
• Score: 14.897162428029878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised low-level vision models rely on pixel-wise losses against paired references, yet paired training sets exhibit per-pair photometric inconsistency, say, different image pairs demand different global brightness, color, or white-balance mappings. This inconsistency enters through task-intrinsic photometric transfer (e.g., low-light enhancement) or unintended acquisition shifts (e.g., de-raining), and in either case causes an optimization pathology. Standard reconstruction losses allocate disproportionate gradient budget to conflicting per-pair photometric targets, crowding out content restoration. In this paper, we investigate this issue and prove that, under least-squares decomposition, the photometric and structural components of the prediction-target residual are orthogonal, and that the spatially dense photometric component dominates the gradient energy. Motivated by this analysis, we propose Photometric Alignment Loss (PAL). This flexible supervision objective discounts nuisance photometric discrepancy via closed-form affine color alignment while preserving restoration-relevant supervision, requiring only covariance statistics and tiny matrix inversion with negligible overhead. Across 6 tasks, 16 datasets, and 16 architectures, PAL consistently improves metrics and generalization. The implementation is in the appendix.

Related papers

• Hyperspectral Intrinsic Decomposition: Joint Recovery of Reflectance and Photometric Components for Non-Lambertian Scenes [29.51510553736925]
  Hyperspectral intrinsic decomposition (HID) aims to disentangle material-related spectral properties and photometric effects in hyperspectral images.<n>Most existing HID studies have been developed under Lambertian or near-Lambertian assumptions.<n>We develop a unified inversion paradigm that reformulates the recovery of four coupled reflectance and photometric components as the estimation of two spectral--spatial target variables.
  arXiv  Detail & Related papers  (2026-07-28T07:26:07Z)
• Con-DSO: Learning Short-Horizon Consistency Priors for RGB-D Direct Sparse Odometry [8.079139316299182]
  Con-DSO is a consistency-aware RGB-D direct sparse odometry framework.<n>It predicts dense photometric and depth-geometric consistency uncertainty from temporally adjacent RGB-D frame pairs.<n>Experiments show substantial gains over direct RGB-D VO baselines.
  arXiv  Detail & Related papers  (2026-05-27T04:46:52Z)
• Architectural Unification for Polarimetric Imaging Across Multiple Degradations [54.83037963738918]
  We propose a unified architectural framework for polarimetric imaging that is structurally shared across multiple degradation scenarios.<n>The model performs single-stage joint image-Stokes processing, avoiding error accumulation and explicitly preserving physical consistency.
  arXiv  Detail & Related papers  (2026-03-06T02:38:57Z)
• Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis [73.27997579020233]
  We propose Luminance-GS++, a 3DGS-based framework for robust NVS under diverse illumination conditions.<n>Our method combines a globally view-adaptive lightness adjustment with a local pixel-wise residual refinement for precise color correction.
  arXiv  Detail & Related papers  (2026-02-20T16:20:50Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• Physically-Based Photometric Bundle Adjustment in Non-Lambertian Environments [59.96101889715997]
  Photometric bundle adjustment (PBA) is widely used in estimating the camera pose and 3D geometry by assuming a Lambertian world. The assumption of photometric consistency is often violated since the non-diffuse reflection is common in real-world environments. We propose a novel physically-based PBA method to solve this problem.
  arXiv  Detail & Related papers  (2024-09-18T10:22:07Z)
• MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images [20.439758719616048]
  Photometric constraint is indispensable for self-supervised monocular depth estimation.<n>Built-in light causes significant brightness fluctuations, making photometric constraint unreliable.<n>We propose MonoPCC to address the brightness inconsistency radically by reshaping the photometric constraint into a cycle form.
  arXiv  Detail & Related papers  (2024-04-25T12:34:23Z)
• Degradation-agnostic Correspondence from Resolution-asymmetric Stereo [96.03964515969652]
  We study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. We propose to impose the consistency between two views in a feature space instead of the image space, named feature-metric consistency. We find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features.
  arXiv  Detail & Related papers  (2022-04-04T12:24:34Z)
• Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo [61.6260594326246]
  We introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. Using separable 4D convolutions and 2D heat-maps reduces the size and makes more efficient.
  arXiv  Detail & Related papers  (2021-03-22T18:06:58Z)

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.