Surflo: Consistent 3D Surface Flow Model with Global State

• URL: http://arxiv.org/abs/2606.13644v1
• Date: Thu, 11 Jun 2026 17:48:38 GMT
• Title: Surflo: Consistent 3D Surface Flow Model with Global State
• Abstract summary: Surflo decodes oriented 3D surface points by independently transporting them from noise onto the surface via flow matching.<n>To suppress the local inconsistencies inherent to independent per-point decoding, an inference-time guidance term correlates nearby points by injecting a photometric gradient.<n>Surflo matches or surpasses feed-forward baselines on surface metrics, runs an order of magnitude faster than optimization-based methods that require hundreds of views, and is the only feed-forward approach to combine a global latent with arbitrary-resolution decoding.
• Score: 57.57234680235885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geometry is invariant to viewpoint, which makes any collection of images a redundant encoding of a single 3D state. Existing feed-forward reconstruction models fail to exploit this: per-view methods emit overlapping, unaligned pointmaps that grow linearly with input count, while global-latent methods commit to a fixed, low-resolution output. We introduce Surflo, which compresses a variable number of unposed RGB views into K latent tokens-one global state-and decodes oriented 3D surface points by independently transporting them from noise onto the surface via flow matching. This frees the output from any fixed grid or token budget: the same latent yields from a few thousand to a million points in a single forward pass. To suppress the local inconsistencies inherent to independent per-point decoding, an inference-time guidance term correlates nearby points by injecting a photometric gradient during ODE integration. Surflo matches or surpasses feed-forward baselines on surface metrics, runs an order of magnitude faster than optimization-based methods that require hundreds of views, and is the only feed-forward approach to combine a global latent with arbitrary-resolution decoding.

Related papers

• WildFab: Multi-Axis 3D Printing from Models in the Wild [4.753066305078767]
  WildFab is a computational framework for multi-axis 3D printing.<n>It computes spatial toolpath and global collision-free motion from input models.
  arXiv  Detail & Related papers  (2026-09-02T10:35:32Z)
• VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction [8.983872448985627]
  We present a scale-consistency enhancement framework built on a key insight: in structured environments such as driving scenes, geometric quantities remain inherently invariant across temporal segments.<n>We propose Scene Geometric Invariant Anchoring (SGIA), which extracts dominant geometric invariants from each chunk's predicted point cloud via coarse-to-fine robust estimation.<n> Experiments on multiple long-sequence benchmarks demonstrate state-of-the-art performance, reducing absolute trajectory error by up to 32% with significant gains in trajectory stability and reconstruction quality.
  arXiv  Detail & Related papers  (2026-08-15T14:32:55Z)
• SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry [69.89196162649091]
  SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry) is a novel approach for estimating 3D geometry from extended monocular video sequences.<n>Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations.
  arXiv  Detail & Related papers  (2026-06-19T10:23:25Z)
• GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens [41.96744884413287]
  We introduce GlobalSplat, a framework built on the principle of align first, decode later.<n>Our approach learns a compact, global, latent scene representation that encodes multi-view input and resolves cross-view correspondences.<n>On RealEstate10K and ACID, our model achieves competitive novel-view synthesis performance while utilizing as few as 16K Gaussians.
  arXiv  Detail & Related papers  (2026-04-16T17:52:06Z)
• TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting [2.441486089588484]
  3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render images.<n>This paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation.<n>We demonstrate the effectiveness of our method across multiple photorealistic datasets, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-06T03:45:39Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimization [18.15181405364316]
  Orienting point clouds is a fundamental problem in computer graphics and 3D vision.<n>We propose DACPO (Divide-And-Conquer Point Orientation), a novel framework for scalable and robust point cloud orientation.<n>We show how DACPO segments the input point cloud into smaller, manageable blocks, processes each block independently, and integrates the results through a global optimization stage.
  arXiv  Detail & Related papers  (2025-05-29T14:21:22Z)
• Multiway Point Cloud Mosaicking with Diffusion and Global Optimization [74.3802812773891]
  We introduce a novel framework for multiway point cloud mosaicking (named Wednesday) At the core of our approach is ODIN, a learned pairwise registration algorithm that identifies overlaps and refines attention scores. Tested on four diverse, large-scale datasets, our method state-of-the-art pairwise and rotation registration results by a large margin on all benchmarks.
  arXiv  Detail & Related papers  (2024-03-30T17:29:13Z)
• Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling [55.05706827963042]
  Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. We propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling.
  arXiv  Detail & Related papers  (2023-12-23T01:52:14Z)
• iPUNet:Iterative Cross Field Guided Point Cloud Upsampling [20.925921503694894]
  Point clouds acquired by 3D scanning devices are often sparse, noisy, and non-uniform, causing a loss of geometric features. We present a learning-based point upsampling method, iPUNet, which generates dense and uniform points at arbitrary ratios. We demonstrate that iPUNet is robust to handle noisy and non-uniformly distributed inputs, and outperforms state-of-the-art point cloud upsampling methods.
  arXiv  Detail & Related papers  (2023-10-13T13:24:37Z)
• Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment [50.892158511845466]
  We show that gradient consistency in the field, indicated by the parallelism of level sets, is the key factor affecting the inference accuracy. We propose a level set alignment loss to evaluate the parallelism of level sets, which can be minimized to achieve better gradient consistency.
  arXiv  Detail & Related papers  (2023-05-19T11:28:05Z)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)

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.