Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction

• URL: http://arxiv.org/abs/2608.11077v1
• Date: Tue, 11 Aug 2026 15:38:55 GMT
• Title: Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction
• Abstract summary: We present Learning Gaussian Structure (LGS), a framework that enhances both Gaussian structure and primitive attributes.<n>Our key observation is that changes in local responses induced by a prune or add intervention reveal whether the structural adjustment benefits reconstruction.<n>We develop a compact Cross-Time Point Query that explicitly retrieves and aggregates neighboring features from Gaussian primitives at other timestamps for reliable attribute prediction.
• Score: 22.26159235291006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feed-forward Gaussian reconstruction has recently emerged as an efficient approach for driving scene reconstruction. However, prevailing LiDAR-based methods preserve the initial correspondence between observed points and Gaussian primitives, treating the initialized primitive set as the final representation. Unlike optimization-based 3DGS, these methods cannot accumulate gradients during training to determine how the scenes representation should be densified. Meanwhile, the shared sparse backbone only fuses observations from different timestamps implicitly, without explicitly aggregating cross-time evidence for individual primitives. In this paper, we present Learning Gaussian Structure (LGS), a framework that enhances both Gaussian structure and primitive attributes. Our key observation is that changes in local gradient responses induced by a prune or add intervention reveal whether the corresponding structural adjustment benefits reconstruction. Based on this observation, our Gaussian Densify Policy learns a Densify Map comprising Prune and Addition Scores from controlled interventions, and directly adjusts the Gaussian structure during inference. We further develop a compact Cross-Time Point Query that explicitly retrieves and aggregates neighboring features from Gaussian primitives at other timestamps for reliable attribute prediction. Extensive experiments on the Waymo Open Dataset and PandaSet demonstrate that LGS consistently outperforms existing methods.

Related papers

• From Uniform to Learned Graph Priors: Diffusion for Structure Discovery [18.139196723025034]
  We propose Diff-prior, a diffusion-parameterized adaptive prior used to calibrate latent graph distribution rather than generate graphs.<n>Our core insight is to reframe prior integration as a learnable denoising-style calibration that organizes scattered, uncertain edge posteriors into a more reliable structure.<n>Experiments on standard benchmarks validated our framework, and the results indicate that Diff-prior improves the performance of structure inference.
  arXiv  Detail & Related papers  (2026-06-10T09:14:45Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting [64.2640656619583]
  Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction.<n>We propose a Retrieval-guided Invariant-Dynamic DEcomposition framework for time series forecasting.
  arXiv  Detail & Related papers  (2026-05-24T07:31:55Z)
• Probability-Conserving Flow Guidance [49.03107678763765]
  Adaptive Manifold Guidance (AdaMaG) improves realism, reduces hallucinations, and controlled desaturation in high-guidance.<n>Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and controlled desaturation in high-guidance.
  arXiv  Detail & Related papers  (2026-05-19T16:34:01Z)
• Scalable Gaussian process inference via neural feature maps [1.0152838128195467]
  We show that the learned feature map can be interpreted as an optimal low-rank approximation to a Gram matrix derived from an implied RKHS.<n>We introduce product feature-map kernels to address oversmoothing.<n>This simple yet powerful approach enables fast, scalable, and accurate exact GP inference with minimal upfront work.
  arXiv  Detail & Related papers  (2026-05-11T09:45:45Z)
• TRSVR: An Adaptive Stochastic Trust-Region Method with Variance Reduction [17.083793956698994]
  We propose a trust method for unconstrained non-reduced optimization that incorporates variance-region (SVRG) to accelerate convergence.<n>The proposed algorithm relies solely on gradient information and does not require function value evaluations.
  arXiv  Detail & Related papers  (2026-01-21T04:41:57Z)
• RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors [54.81109375939306]
  RGE-GS is a novel expansive reconstruction framework that synergizes diffusion-based generation with reward-guided Gaussian integration.<n>We propose a reward network that learns to identify and prioritize consistently generated patterns prior to reconstruction phases.<n>During the reconstruction process, we devise a differentiated training strategy that automatically adjust Gaussian optimization progress according to scene converge metrics.
  arXiv  Detail & Related papers  (2025-06-28T08:02:54Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Time-series attribution maps with regularized contrastive learning [1.5503410315996757]
  gradient-based attribution methods aim to explain decisions of deep learning models but so far lack identifiability guarantees.<n>Here, we propose a method to generate attribution maps with identifiability guarantees by developing a regularized contrastive learning algorithm trained on time-series data.<n>We show theoretically that xCEBRA has favorable properties for identifying the Jacobian matrix of the data generating process.
  arXiv  Detail & Related papers  (2025-02-17T18:34:25Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes [38.157373733083894]
  This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network. The framework is based on reducing the neural aspect to a prediction of a matrix for a single point, conditioned on a global shape descriptor. By operating in the intrinsic gradient domain of each individual mesh, it allows the framework to predict highly-accurate mappings.
  arXiv  Detail & Related papers  (2022-05-05T19:51:13Z)

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.