RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer

• URL: http://arxiv.org/abs/2607.12495v1
• Date: Tue, 14 Jul 2026 08:27:28 GMT
• Title: RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer
• Abstract summary: A promising approach is to transfer visual attributes from real images onto synthetic 3D surfaces.<n>Traditional methods struggle with resolution mismatch and the inherent discreteness of point correspondences.<n>We propose RealSkin, a self-supervised framework that performs correspondence optimization in a learned spectral domain.
• Score: 22.636806561877606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Creating photorealistic 3D assets requires bridging the appearance gap between real-world observations and synthetic models. A promising approach is to transfer visual attributes from real images onto synthetic 3D surfaces. Traditional methods struggle with resolution mismatch and the inherent discreteness of point correspondences. In contrast, resolution-robust functional maps enable smooth attribute propagation but rely on near-isometry assumptions and topological consistency. To address these limitations, we propose RealSkin, a self-supervised framework that performs correspondence optimization in a learned spectral domain, guided by spatial correspondences. We first introduce a spatial-guided registration algorithm to establish coarse correspondences under severe topological discrepancies. To relax strict isometric assumptions and handle partial correspondences, we further design a spectral-aware neural adjoint network that incorporates partial correspondences into a neural function space and models non-isometric residuals for correspondence refinement. Experimental results demonstrate that our method achieves state-of-the-art performance on challenging real-to-synthetic scenarios. The code will be publicly released.

Related papers

• Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models [9.722829662835233]
  We show that modern Vision-Language Models (VLMs) possess a latent topological map of 3D scenes.<n>By isolating this spatial subspace through cross-scene linear feature extraction, we extract a clean spatial subspace that causally controls the model's spatial outputs.<n>We mathematically shape this latent representation and prove its correspondence to the Laplacian eigenmaps of the scene's 3D Gaussian- kernel graph.
  arXiv  Detail & Related papers  (2026-05-08T02:32:27Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation [17.52581598592474]
  Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions.<n>We propose a method combining an SO(3)-equivariant convolutional implicit network and a positive-incentive point sampling (PIPS) strategy.<n>Our method outperforms the state-of-the-art on three pose estimation datasets.
  arXiv  Detail & Related papers  (2026-02-23T15:10:00Z)
• Robust Mesh Saliency GT Acquisition in VR via View Cone Sampling and Geometric Smoothing [59.12032628787018]
  3D mesh saliency ground truth is essential for human-centric visual modeling in virtual reality (VR)<n>Current VR eye-tracking pipelines rely on single ray sampling and Euclidean smoothing, triggering texture attention and signal leakage across gaps.<n>This paper proposes a robust framework to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T05:20:12Z)
• Features Emerge as Discrete States: The First Application of SAEs to 3D Representations [5.751184796461698]
  Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations.<n>We present the first application of SAEs to the 3D domain, analyzing the features used by a state-of-the-art 3D reconstruction VAE applied to 53k 3D models.
  arXiv  Detail & Related papers  (2025-12-12T03:54:45Z)
• Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes [14.372634421912094]
  We introduce a novel approach for analytically extracting surfaces from neural implicit functions.<n>Our method operates in parallel and can navigate large neural architectures.<n>The resulting meshes faithfully capture the full geometric information from the network without ad-hoc spatial discretization.
  arXiv  Detail & Related papers  (2025-09-25T11:06:42Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Neural Semantic Surface Maps [52.61017226479506]
  We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement.
  arXiv  Detail & Related papers  (2023-09-09T16:21:56Z)
• Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis [17.920305227880245]
  Our paper formulates triple vision tasks in a consistent manner using approximate analysis-by-synthesis. We show that our analysis-by-synthesis is much more robust than conventional neural networks when evaluated on real-world images.
  arXiv  Detail & Related papers  (2023-05-31T18:45:02Z)
• Explicit Correspondence Matching for Generalizable Neural Radiance Fields [66.99907718824782]
  We present a new NeRF method that is able to generalize to new unseen scenarios and perform novel view synthesis with as few as two source views.<n>The explicit correspondence matching is quantified with the cosine similarity between image features sampled at the 2D projections of a 3D point on different views.<n>Our method achieves state-of-the-art results on different evaluation settings, with the experiments showing a strong correlation between our learned cosine feature similarity and volume density.
  arXiv  Detail & Related papers  (2023-04-24T17:46:01Z)
• Scene Synthesis via Uncertainty-Driven Attribute Synchronization [52.31834816911887]
  This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches.
  arXiv  Detail & Related papers  (2021-08-30T19:45:07Z)

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.