From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance

• URL: http://arxiv.org/abs/2606.26007v1
• Date: Wed, 24 Jun 2026 16:26:53 GMT
• Title: From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance
• Abstract summary: Image priors can synthesize target conditions for 3D Gaussian street scenes, but independently edited views do not define a coherent 3D target.<n>To address this gap, teacher-relative appearance residual distillation is introduced for appearance baking.<n>A structured space for frequency decomposition, confidence estimation, and primitive-level lifting is formed by residuals between teacher anchors and original renders.
• Score: 13.51195065028002
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image priors can synthesize target conditions for 3D Gaussian street scenes, but independently edited views do not define a coherent 3D target. Direct fitting can propagate view-specific noise, while existing pipelines do not jointly handle imperfect sparse anchors and standard-rasterizer deployment. To address this gap, teacher-relative appearance residual distillation is introduced for appearance baking. A structured space for frequency decomposition, confidence estimation, and primitive-level lifting is formed by residuals between teacher anchors and original renders. The direct optimization signal is supplied by renderer-space matching, while primitive assignment is regularized by support-aware Gaussian-space aggregation. Supported detail is admitted and unsupported noise is suppressed through confidence-gated coarse-to-fine optimization, after which all residuals are baked into fixed-geometry spherical-harmonic coefficients. The teacher and auxiliary training modules are discarded at inference. Evaluation across Waymo street assets, Tanks and Temples scenes, and multiple target conditions shows a favorable overall balance of target alignment, content preservation, artifact suppression, and cross-view consistency over editing-based baselines. Ablations confirm the effectiveness of the main components. Code will be released at https://github.com/Cagares/Baking-for-3D-Gaussian.

Related papers

• Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison [25.854113650180736]
  Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs.<n>We introduce Gekko, which turns this limitation into a useful signal.<n>Gekko is a network, trained from scratch, that jointly performs cross-view completion, masked autoencoding, and per-pixel prediction.
  arXiv  Detail & Related papers  (2026-09-01T16:57:46Z)
• Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats [91.55220894541151]
  3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance.<n>We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context.
  arXiv  Detail & Related papers  (2026-08-16T09:43:50Z)
• Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images [62.31892851760248]
  COVScene is a pose-free semantic Gaussian framework that couples renderable primitives with a dense semantic occupancy field.<n>We show that COVScene maintains competitive rendering quality, improves open-vocabulary segmentation, and achieves stronger semantic occupancy prediction than the self-supervised baseline.
  arXiv  Detail & Related papers  (2026-07-02T03:00:23Z)
• Visual Geometry Transformer in the Wild: Distractor-Free 3D Reconstruction [77.75911117889915]
  Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption.<n>This reliance on idealized inputs causes even the most advanced methods to fail in real-world settings.<n>We propose Visual Geometry Transformer in the Wild, an end-to-end framework for robust reconstruction from inconsistent views.
  arXiv  Detail & Related papers  (2026-06-22T02:52:22Z)
• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting [41.21645092733966]
  We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features.<n> Experiments show that our method enhances the accuracy of lifted semantics, providing an efficient and effective approach to robust 3D semantic Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-24T10:57:05Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenes [10.279549537925062]
  3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation.<n>To address the issues of unstable pose estimation and scene representation distortion, we approach the problem from two aspects.<n>For pose estimation, we leverage LiDAR-IMU Odometry to provide prior poses for cameras in large-scale environments.<n>For scene representation, we introduce normal vector constraints and effective rank regularization to enforce consistency in the direction and shape of Gaussian primitives.
  arXiv  Detail & Related papers  (2025-11-10T06:45:08Z)
• Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation [15.196083762043004]
  We propose a novel 3D-AVS-SS approach named SAD-Splat to address semantic ambiguity in aerial images.<n>Our method integrates semantic confidence estimation with a learnable sparsity mechanism based on the Hard Concrete distribution.<n>It achieves an excellent balance between segmentation accuracy and representation compactness.
  arXiv  Detail & Related papers  (2025-08-13T08:57:38Z)
• TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancy [14.075911467687789]
  We propose a target-scale adaptive, symmetric retrieval mechanism for 3D semantic occupancy prediction.<n>It expands the neighborhood for large targets to enhance context awareness and shrinks it for small ones to improve efficiency and suppress noise.<n>In summary, we propose TACOcc, an adaptive multi-modal fusion framework for 3D semantic occupancy prediction, enhanced by volume rendering supervision.
  arXiv  Detail & Related papers  (2025-05-19T04:32:36Z)
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)

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.