CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction

• URL: http://arxiv.org/abs/2607.13492v1
• Date: Wed, 15 Jul 2026 06:38:23 GMT
• Title: CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction
• Abstract summary: High-fidelity indoor surface reconstruction remains a significant challenge.<n>Existing approaches often rely on spatially indiscriminate prior supervision and a scene-global SDF-to-density transformation.<n>We propose a unified framework that addresses this challenge via complementary adaptations of supervision and representation capacity.
• Score: 16.213539439407754
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, high-fidelity indoor surface reconstruction remains a significant challenge, primarily due to the pronounced \emph{geometric heterogeneity} of indoor scenes. Large texture-less planar regions typically require stronger regularization to suppress high-frequency artifacts, while thin structures demand sharper, more adaptive representations to mitigate the spectral bias of multi-layer perceptrons (MLPs) and prevent over-smoothing. Existing approaches often rely on spatially indiscriminate prior supervision and a scene-global SDF-to-density transformation, which constrains their ability to balance planar smoothness and detail preservation. In this paper, we propose CASA-SDF (Curriculum-Aware Spatial Adaptation for SDF), a unified framework that addresses this challenge via complementary adaptations of supervision and representation capacity. Specifically, Hybrid Spatially-Adaptive Uncertainty Annealing (SAUA) fuses semantic and photometric uncertainties to construct a pixel-wise curriculum for monocular prior supervision. This strategy maintains regularization in reliable regions while attenuating unreliable supervision early in training to enable data-driven photometric refinement. Meanwhile, Curvature-Aware Locally Adaptive Density Transformation (CALADT) progressively modulates the sharpness of the SDF-to-density mapping via a curvature proxy to enhance the representation of thin structures. Extensive experiments on benchmark indoor datasets demonstrate that CASA-SDF improves surface completeness and detail recovery on high-frequency structures, without compromising the stability of planar surfaces.

Related papers

• NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning [11.616195899650146]
  We introduce NeuDonatello, a novel framework that models and leverages SDF uncertainty to improve surface reconstruction.<n>We develop an adaptive regularization that strengthens geometric constraints where RGB supervision is unreliable, avoiding incorrect surface reconstruction.<n>Experiments demonstrate that NeuDonatello achieves state-of-the-art reconstruction accuracy, with robust performance across diverse scenes using only posed RGB images.
  arXiv  Detail & Related papers  (2026-08-27T01:03:35Z)
• Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction [56.51413081953813]
  SurfSVR is a novel sparse voxel reconstruction paradigm that treats 2D surface priors as explicit 3D geometric regularizers.<n>It consistently improves sparse voxel reconstruction across scenes with substantially different visibility and geometry characteristics.
  arXiv  Detail & Related papers  (2026-08-12T11:25:31Z)
• CLUIE: Clustering-Aware Recurrent Propagation with Local Structural Compensation for Underwater Image Enhancement [92.78545064386485]
  Underwater image enhancement remains challenging due to wavelength-dependent light absorption, scattering, and backscattering.<n>We propose a Clustering-aware RWKV framework, which reformulates the fixed recurrent propagation path of conventional RWKV into a content-adaptive token trajectory.<n>Experiments on multiple underwater image enhancement benchmarks demonstrate that CRWKV achieves state-of-the-art quantitative performance and superior visual quality.
  arXiv  Detail & Related papers  (2026-07-23T16:09:36Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians [57.95719610327081]
  We propose an Atlanta-world guided implicit-structured Gaussian Splatting that achieves smooth indoor and urban scene reconstruction.<n>Our method outperforms state-of-the-art approaches in both indoor and urban scenes, delivering superior surface reconstruction quality.
  arXiv  Detail & Related papers  (2025-10-29T03:17:58Z)
• Edge-Aware Normalized Attention for Efficient and Detail-Preserving Single Image Super-Resolution [27.3322913419539]
  Single-image super-resolution (SISR) remains highly ill-posed because recovering structurally faithful high-frequency content from a single low-resolution observation is ambiguous.<n>Existing edge-aware methods often attach edge priors or attention branches onto increasingly complex backbones, yet ad hoc fusion frequently introduces redundancy, unstable optimization, or limited structural gains.<n>We address this gap with an edge-guided attention mechanism that derives an adaptive modulation map from jointly encoded edge features and intermediate feature activations, then applies it to normalize and reweight responses, selectively amplifying structurally salient regions while suppressing spurious textures.
  arXiv  Detail & Related papers  (2025-09-18T02:31:24Z)
• HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity [8.74691272469226]
  HiNeuS is a unified framework that holistically addresses three core limitations in existing approaches.<n>We introduce: 1) Differential visibility verification through SDF-guided ray tracing; 2) Planar-conformal regularization via ray-aligned geometry patches; and 3) Physically-grounded Eikonal relaxation that dynamically modulates geometric constraints based on local gradients.
  arXiv  Detail & Related papers  (2025-06-30T13:45:25Z)
• RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
  We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor. Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:54:25Z)
• PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction [31.768161784030923]
  The framework PSDF is proposed which resorts to external geometric priors from a pretrained MVS network and internal geometric priors inherent in the NISR model. Experiments on the Tanks and Temples dataset show that PSDF achieves state-of-the-art performance on complex uncontrolled scenes.
  arXiv  Detail & Related papers  (2024-01-23T13:30:43Z)
• Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement [50.56517624931987]
  The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations.
  arXiv  Detail & Related papers  (2023-09-14T12:05:29Z)
• DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction [34.07747722661987]
  This paper focuses on the utilization of uncertainty in monocular priors and the bias in SDF-based volume rendering. We propose an uncertainty modeling technique that associates larger uncertainties with larger errors in the monocular priors. High-uncertainty priors are then excluded from optimization to prevent bias.
  arXiv  Detail & Related papers  (2023-08-29T18:00:22Z)

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.