From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2605.07203v2
• Date: Mon, 11 May 2026 01:43:52 GMT
• Title: From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting
• Abstract summary: We provide evidence that native primitive attributes alone carry sufficient signal for scene change detection.<n> operating directly on primitives gives our method, GD-DIFF, two properties that distinguish it from render-then-compare methods.
• Score: 8.895952132148304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene change detection methods built on Gaussian splatting universally follow a render-then-compare paradigm: the pre-change scene is rendered into 2D and compared against post-change images via pixel or feature residuals. This change detection problem with Gaussian Splatting has been treated as a question about pixels; we treat it as a question about primitives. We provide direct evidence that native primitive attributes alone -- position, anisotropic covariance, and color -- carry sufficient signal for scene change detection. What makes primitive-space comparison hard is the under-constrained nature of Gaussian splatting representation: independent optimizations yield primitive solutions whose count, positions, shapes, and colors differ even where nothing has changed. We address this challenge with anisotropic models of geometric and photometric drift, complemented by a per-primitive observability term that reflects the extent to which each Gaussian is constrained by the camera geometry. Operating directly on primitives gives our method, GD-DIFF, two properties that distinguish it from render-then-compare methods. First, change maps are multi-view consistent by construction, where prior work had to learn this through an additional optimization objective. Second, geometric and appearance changes are scored separately, identifying not just where but what kind of change occurred, distinguishing structural changes (e.g., an added object) from surface-level ones (e.g., a color change) without supervision or external model dependencies. On real-world benchmarks, GS-DIFF surpasses the prior state-of-the-art approach by $\sim$17% in mean Intersection over Union.

Related papers

• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification [52.517763621139956]
  3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis.<n>Standard adaptive density control relies on screen-space positional gradients.<n>We present a structure-aware densification framework for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-30T15:37:20Z)
• A Hypertoroidal Covering for Perfect Color Equivariance [3.793458006209272]
  We introduce a color equivariant architecture that is truly equivariant.<n>Instead of approximating the interval with the real line, we lift values on the interval to values on the circle (a double-cover) and build equivariant representations there.<n>Our approach resolves the approximation artifacts of previous methods, improves interpretability and generalizability, and achieves better predictive performance than conventional and equivariant baselines on tasks such as fine-grained classification and medical imaging tasks.
  arXiv  Detail & Related papers  (2026-03-04T16:43:02Z)
• Learning Geometric Invariance for Gait Recognition [43.26239161303881]
  We argue that variations in different gait conditions can be approximately viewed as a combination of geometric transformations.<n>We design a $mathcalR$eflect-$mathcalR$otate-$mathcalS$cale invariance learning framework, named $mathcalRRS$-Gait.<n>Experiments on four popular gait datasets show superior performance across various gait conditions.
  arXiv  Detail & Related papers  (2026-01-09T07:47:01Z)
• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• Rigidity-Aware 3D Gaussian Deformation from a Single Image [12.08044152819999]
  We present DeformSplat, a novel framework that guides 3D Gaussian deformation from only a single image.<n>We also present Gaussian-to-Pixel Matching which bridges the domain gap between 3D Gaussian representations and 2D pixel observations.<n>By combining these two techniques, our approach can reconstruct consistent deformations from a single image.
  arXiv  Detail & Related papers  (2025-09-26T11:34:55Z)
• Detect Changes like Humans: Incorporating Semantic Priors for Improved Change Detection [52.62459671461816]
  This paper explores incorporating semantic priors from visual foundation models to improve the ability to detect changes.<n>Inspired by the human visual paradigm, a novel dual-stream feature decoder is derived to distinguish changes by combining semantic-aware features and difference-aware features.
  arXiv  Detail & Related papers  (2024-12-22T08:27:15Z)
• Hybrid Explicit Representation for Ultra-Realistic Head Avatars [55.829497543262214]
  We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time.<n> UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures.<n>Experiments that our modeled results exceed those of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-03-18T04:01:26Z)
• MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations [2.2954246824369218]
  We propose a novel model that generates augmenting transformations in a multimodal latent space of geometric deformations.<n> Experimental results show that our proposed approach outperforms all baselines by significantly improved prediction accuracy.
  arXiv  Detail & Related papers  (2023-12-20T21:30:55Z)
• Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive Architecture [7.825153552141346]
  We propose a Geometric Transformation Sensitive Architecture to be sensitive to geometric transformations. Our method encourages the student to be sensitive by predicting rotation and using targets that vary with those transformations. Our approach demonstrates improved performance when using non-object-centric images as pretraining data.
  arXiv  Detail & Related papers  (2023-04-17T06:32:37Z)
• Learning Transformations To Reduce the Geometric Shift in Object Detection [60.20931827772482]
  We tackle geometric shifts emerging from variations in the image capture process. We introduce a self-training approach that learns a set of geometric transformations to minimize these shifts. We evaluate our method on two different shifts, i.e., a camera's field of view (FoV) change and a viewpoint change.
  arXiv  Detail & Related papers  (2023-01-13T11:55:30Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)
• Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild [96.09941542587865]
  We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.
  arXiv  Detail & Related papers  (2020-07-17T12:34:38Z)

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.