ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare

• URL: http://arxiv.org/abs/2603.09968v1
• Date: Tue, 10 Mar 2026 17:58:08 GMT
• Title: ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare
• Abstract summary: We present ReCoSplat, an autoregressive feed-forward Gaussian Splatting model supporting posed or unposed inputs.<n>Code and pretrained models will be released.
• Score: 53.16118137855849
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-forward Gaussian Splatting model supporting posed or unposed inputs, with or without camera intrinsics. While assembling local Gaussians using camera poses scales better than canonical-space prediction, it creates a dilemma during training: using ground-truth poses ensures stability but causes a distribution mismatch when predicted poses are used at inference. To address this, we introduce a Render-and-Compare (ReCo) module. ReCo renders the current reconstruction from the predicted viewpoint and compares it with the incoming observation, providing a stable conditioning signal that compensates for pose errors. To support long sequences, we propose a hybrid KV cache compression strategy combining early-layer truncation with chunk-level selective retention, reducing the KV cache size by over 90% for 100+ frames. ReCoSplat achieves state-of-the-art performance across different input settings on both in- and out-of-distribution benchmarks. Code and pretrained models will be released. Our project page is at https://freemancheng.com/ReCoSplat .

Related papers

• AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting [21.638608939423673]
  2D Gaussian splatting provides an efficient explicit representation for image reconstruction.<n>Existing methods still require costly per-image iterative optimization or rely on handcrafted priors for primitive allocation.<n>We present AIR, a self-supervised feed-forward framework that amortizes iterative Gaussian fitting into a single network pass.
  arXiv  Detail & Related papers  (2026-05-20T07:17:22Z)
• ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis [10.752176613697912]
  We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images.<n>We show that ViewSplat achieves state-of-the-art fidelity while maintaining fast inference and real-time rendering.
  arXiv  Detail & Related papers  (2026-03-26T10:03:44Z)
• TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction [45.41545304485825]
  TokenSplat is a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation.<n>At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module.<n>It aggregates multi-scale contextual features to enable long-range cross-view reasoning.
  arXiv  Detail & Related papers  (2026-02-28T15:13:13Z)
• From Rays to Projections: Better Inputs for Feed-Forward View Synthesis [26.130973137744018]
  Feed-forward view synthesis models predict a novel view in a single pass with minimal 3D inductive bias.<n>Existing works encode cameras as Plcker ray maps, which tie predictions to the arbitrary world coordinate gauge and make them sensitive to small camera transformations.<n>We propose projective conditioning, which replaces raw camera parameters with a target-view projective cue that provides a stable 2D input.
  arXiv  Detail & Related papers  (2026-01-08T17:03:44Z)
• iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion [62.09575122593993]
  iGaussian is a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion.<n> Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T&T+DB datasets demonstrate a significant performance improvement over previous methods.
  arXiv  Detail & Related papers  (2025-11-18T05:22:22Z)
• YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting [79.38712054342625]
  YoNoSplat is a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary number of images.<n>Our model is highly versatile, operating effectively with both posed and unposed, calibrated and uncalibrated inputs.<n>It achieves state-of-the-art performance on standard benchmarks in both pose-free and pose-dependent settings.
  arXiv  Detail & Related papers  (2025-11-10T17:21:54Z)
• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views [68.94737256959661]
  AnySplat is a feed forward network for novel view synthesis from uncalibrated image collections.<n>A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance.<n>In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios.
  arXiv  Detail & Related papers  (2025-05-29T17:49:56Z)
• 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)
• COLMAP-Free 3D Gaussian Splatting [88.420322646756]
  We propose a novel method to perform novel view synthesis without any SfM preprocessing. We process the input frames in a sequential manner and progressively grow the 3D Gaussians set by taking one input frame at a time. Our method significantly improves over previous approaches in view synthesis and camera pose estimation under large motion changes.
  arXiv  Detail & Related papers  (2023-12-12T18:39:52Z)

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.