Speed3R: Sparse Feed-forward 3D Reconstruction Models

• URL: http://arxiv.org/abs/2603.08055v1
• Date: Mon, 09 Mar 2026 07:46:51 GMT
• Title: Speed3R: Sparse Feed-forward 3D Reconstruction Models
• Abstract summary: We introduce Speed3R, an end-to-end trainable model inspired by the core principle of Structure-from-Motion.<n>Speed3R features a dual-branch attention mechanism where a compression branch creates a coarse contextual prior to guide a selection branch.<n>This strategy mimics the efficiency of traditional keypoint matching, achieving a remarkable 12.4x inference speedup on 1000-view sequences.
• Score: 15.534969350839788
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive computational bottleneck that severely limits inference speed. To resolve this, we introduce Speed3R, an end-to-end trainable model inspired by the core principle of Structure-from-Motion: that a sparse set of keypoints is sufficient for robust pose estimation. Speed3R features a dual-branch attention mechanism where a compression branch creates a coarse contextual prior to guide a selection branch, which performs fine-grained attention only on the most informative image tokens. This strategy mimics the efficiency of traditional keypoint matching, achieving a remarkable 12.4x inference speedup on 1000-view sequences, while introducing a minimal, controlled trade-off in geometric accuracy. Validated on standard benchmarks with both VGGT and $π^3$ backbones, our method delivers high-quality reconstructions at a fraction of computational cost, paving the way for efficient large-scale scene modeling.

Related papers

• PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur [9.855875137621622]
  We address the inverse problem of blind 3D scene reconstruction from extremely motion-red images.<n>Existing approaches typically circumvent this bottleneck by relying on impractical sharp-image supervision.<n>We introduce PRISM3D, a unified framework enabling robust reconstruction directly from severely degraded inputs.
  arXiv  Detail & Related papers  (2026-07-04T12:45:11Z)
• BA-T: An Iterative Transformer for Two-View Bundle Adjustment [53.16990349592508]
  We propose BA-T, an iterative Transformer that implements BA-style structured updates as a repeatable layer in implicit token space.<n> experiments demonstrate that BA-T progressively improves pose and reconstruction accuracy across iterations.<n>BA-T provides a compact, efficient, and structural alternative to depth-heavy attention, enabling accurate 3D reconstruction within a lightweight architecture.
  arXiv  Detail & Related papers  (2026-06-02T07:51:14Z)
• Geometric Context Transformer for Streaming 3D Reconstruction [51.19524805829903]
  LingBot-Map is a feed-forward 3D foundation model for reconstructing scenes from streaming data.<n>A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory.<n>This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs.
  arXiv  Detail & Related papers  (2026-04-15T17:58:13Z)
• Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias [70.88698584478983]
  We present SparseGen, a novel framework for efficient image-to-3D generation.<n>We model scenes with a compact sparse set of learned 3D anchor queries and a learned expansion operator.<n>Our results argue that sparse set-latent expansion is a principled, practical alternative for efficient 3D generative modeling.
  arXiv  Detail & Related papers  (2026-04-15T14:15:02Z)
• S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models [15.408916900664783]
  Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention.<n>We introduce textbfS-VGGT, a novel approach that addresses redundancy at the structural frame level.<n>S-VGGT is entirely to token-level acceleration methods, allowing the two to be seamlessly combined for compounded speedups.
  arXiv  Detail & Related papers  (2026-03-18T11:42:55Z)
• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory [97.14005794889134]
  We present LoGeR, a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization.<n>LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning.<n>This memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference.
  arXiv  Detail & Related papers  (2026-03-03T18:55:37Z)
• Fast-SAM3D: 3Dfy Anything in Images but Faster [65.17322167628367]
  SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency.<n>We present textbfFast-SAM3D, a training-free framework that aligns computation with instantaneous generation complexity.
  arXiv  Detail & Related papers  (2026-02-05T04:27:59Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction [24.582810014546524]
  We present PLANING, an efficient on-the-fly reconstruction framework built on a hybrid representation.<n>PLANING improves dense mesh Chamfer-L2 by 18.52% over PGSR, surpasses ARTDECO by 1.31 dB PSNR, and reconstructs ScanNetV2 scenes in under 100 seconds.<n>PLANING makes it well suited for a broad range of downstream applications, such as enabling large-scale scene modeling and simulation-ready environments for embodied AI.
  arXiv  Detail & Related papers  (2026-01-29T17:47:26Z)
• SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes [30.52500975808177]
  3D reconstruction in large-scale scenes is a fundamental task in 3D perception.<n>Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times.<n>We propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction.
  arXiv  Detail & Related papers  (2025-11-23T05:03:49Z)
• Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image [68.55613894952177]
  We introduce textbfWonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images.<n>We propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images.<n> Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about $3$ minute in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2025-11-03T17:24:18Z)
• PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation [18.771349697842947]
  This work introduces the Pattern Reuse Graph Conal Network (PRGCN), a novel framework that formalizes pose estimation as a problem of pattern retrieval and adaptation.<n>At its core, PRGCN features a graph memory bank that learns and stores a compact set of pose prototypes, encoded as relational graphs, which are dynamically retrieved via an attention mechanism to provide structured priors.<n>Our work posits that PRGCN establishes a new state-of-the-art, achieving an MPJPE of 37.1mm and 13.4mm, respectively, while exhibiting enhanced cross-domain generalization capability.
  arXiv  Detail & Related papers  (2025-10-22T11:12:07Z)
• FastVGGT: Training-Free Acceleration of Visual Geometry Transformer [83.67766078575782]
  VGGT is a state-of-the-art feed-forward visual geometry model.<n>We propose FastVGGT, which leverages token merging in the 3D domain through a training-free mechanism for accelerating VGGT.<n>With 1000 input images, FastVGGT achieves a 4x speedup over VGGT while mitigating error accumulation in long-sequence scenarios.
  arXiv  Detail & Related papers  (2025-09-02T17:54:21Z)
• iLRM: An Iterative Large 3D Reconstruction Model [34.69940725179257]
  We introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism.<n> Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed.
  arXiv  Detail & Related papers  (2025-07-31T06:33:07Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)
• Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging [7.601695814245209]
  We consider the problem of video snapshot compressive imaging (SCI), where sequential high-speed frames are modulated by different masks and captured by a single measurement. By combining optimization algorithms and neural networks, deep unfolding networks (DUNs) score tremendous achievements in solving inverse problems.
  arXiv  Detail & Related papers  (2023-06-20T06:25:48Z)

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.