Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison

• URL: http://arxiv.org/abs/2609.01530v1
• Date: Tue, 01 Sep 2026 16:57:46 GMT
• Title: Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
• Abstract summary: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs.<n>We introduce Gekko, which turns this limitation into a useful signal.<n>Gekko is a network, trained from scratch, that jointly performs cross-view completion, masked autoencoding, and per-pixel prediction.
• Score: 25.854113650180736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the cross-view reconstruction error over a masked-autoencoder error is a self-supervised proxy for co-visibility: large improvements indicate co-visible regions, negligible ones non-co-visible areas. Gekko is a network, trained from scratch, that jointly performs cross-view completion, masked autoencoding, and per-pixel prediction of this relative improvement, providing an additional binocular signal for all masked regions without any ground-truth 3D annotation. Under identical architectures and training data, Gekko consistently outperforms CroCo on zero-shot correspondence estimation, relative pose estimation, and pointmap regression, with up to 6 times higher accuracy at the strictest relative-pose threshold and a 22% drop in end-point error on ETH3D. The extra channel it learns is itself a strong co-visibility detector on unseen scenes, and Gekko's frozen features outperform released cross-view backbones of comparable or larger size. It can also be trained directly from raw videos with a simple stride-based curriculum, removing the cumbersome 3D preprocessing prior methods require while matching models trained on curated data. Code and pre-trained models are publicly available.

Related papers

• From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance [13.51195065028002]
  Image priors can synthesize target conditions for 3D Gaussian street scenes, but independently edited views do not define a coherent 3D target.<n>To address this gap, teacher-relative appearance residual distillation is introduced for appearance baking.<n>A structured space for frequency decomposition, confidence estimation, and primitive-level lifting is formed by residuals between teacher anchors and original renders.
  arXiv  Detail & Related papers  (2026-06-24T16:26:53Z)
• Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself [38.95274911975506]
  Free Geometry is a framework that enables feed-forward 3D reconstruction models to self-evolve at test time without any 3D ground truth.<n>Our approach consistently improves state-of-the-art foundation models, including Depth Anything 3 and VGGT, across 4 benchmark datasets.
  arXiv  Detail & Related papers  (2026-04-15T16:24:03Z)
• Detect Anything via Next Point Prediction [51.55967987350882]
  Rex- Omni is a 3B-scale MLLM that achieves state-of-the-art object perception performance.<n>On benchmarks like COCO and LVIS, Rex- Omni attains performance comparable to or exceeding regression-based models.
  arXiv  Detail & Related papers  (2025-10-14T17:59:54Z)
• Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression [23.65253469577653]
  We introduce Alligat0R, a novel pre-training approach that reformulates cross-view learning as a co-visibility segmentation task.<n>Our method predicts whether each pixel in one image is co-visible in the second image, occluded, or outside the field of view (FOV)<n>To support this, we present Cub3, a large-scale dataset with 2.5 million image pairs and dense co-visibility annotations.
  arXiv  Detail & Related papers  (2025-03-10T17:29:48Z)
• 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)
• Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning [61.14132533712537]
  We propose MAL-UPC, a framework that effectively leverages both region-level and category-specific geometric similarities to complete missing structures.<n>Our MAL-UPC does not require any 3D complete supervision and only necessitates single-view partial observations in the training set.
  arXiv  Detail & Related papers  (2024-07-13T06:53:39Z)
• GLACE: Global Local Accelerated Coordinate Encoding [66.87005863868181]
  Scene coordinate regression methods are effective in small-scale scenes but face significant challenges in large-scale scenes. We propose GLACE, which integrates pre-trained global and local encodings and enables SCR to scale to large scenes with only a single small-sized network. Our method achieves state-of-the-art results on large-scale scenes with a low-map-size model.
  arXiv  Detail & Related papers  (2024-06-06T17:59:50Z)
• A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation [12.499361832561634]
  We present a unified bird's-eye view (BEV) model for jointly learning of 3D local features and overlap estimation. Our method significantly outperforms existing methods on overlap prediction, especially in scenes with small overlaps.
  arXiv  Detail & Related papers  (2023-02-28T12:01:16Z)
• Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder [63.77257588569852]
  We present 3D Occlusion Auto-Encoder (3D-OAE) for learning representations for point clouds. Our key idea is to randomly occlude some local patches of the input point cloud and establish the supervision via recovering the occluded patches. In contrast with previous methods, our 3D-OAE can remove a large proportion of patches and predict them only with a small number of visible patches.
  arXiv  Detail & Related papers  (2022-03-26T14:06:29Z)
• SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning [114.58986229852489]
  In this paper, we explore the basic and generic supervision in the sequence from spatial, sequential and temporal perspectives. We derive a particular form named Contrastive Learning (SeCo) SeCo shows superior results under the linear protocol on action recognition, untrimmed activity recognition and object tracking.
  arXiv  Detail & Related papers  (2020-08-03T15:51:35Z)

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.