CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild

• URL: http://arxiv.org/abs/2607.00321v1
• Date: Wed, 01 Jul 2026 01:38:29 GMT
• Title: CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild
• Abstract summary: CORGI is a novel framework for consistency-aware 3D dog reconstruction from a single unconstrained image.<n>To overcome generative inconsistencies and the lack of multi-view capture, our pipeline introduces three core components.<n>We show that CORGI achieves state-of-the-art performance, generalizing seamlessly across diverse dog breeds.
• Score: 13.416281912804633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing high-fidelity 3D models of highly articulated animals, such as dogs, from a single in-the-wild image remains a formidable challenge. In this paper, we introduce CORGI, a novel framework for consistency-aware 3D dog reconstruction from a single unconstrained image that completely eliminates the need for 3D supervision. To overcome generative inconsistencies and the lack of multi-view capture, our pipeline introduces three core components. First, we propose a Canonical-Driven Orbital Generation (CDOG) strategy, utilizing specialized Canonical and Orbit LoRAs to normalize arbitrary input poses and synthesize reliable 360-degree video observations. Second, we design a Consistency-aware Deformable 3DGS (CA-3DGS) module that anchors on a D-SMAL prior, explicitly modeling per-view generative errors through dedicated neural deformation fields to learn accurate vertex-level displacements. Finally, to eliminate structural distortions and recover high-frequency details, we introduce a self-supervised Deformation-Conditioned Generative Repair (DCGR) module. Extensive experiments demonstrate that CORGI achieves state-of-the-art performance, generalizing seamlessly across diverse dog breeds to produce geometrically accurate, visually coherent, and fully animatable 3D assets ready for downstream applications.

Related papers

• Axolotl3D: a Unified Framework for Faithful 3D Shape Completion [1.6934548577260198]
  We present Axolotl3D, a 3D generation model that conditions on images, visibility masks, camera parameters, and a partial point cloud.<n>A unified training strategy synthesizes diverse conditioning regimes from large-scale 3D data, enabling robust cross-modal reasoning.<n>Experiments on Toys4K and OmniObject3D demonstrate state-of-the-art performance under both clean and occluded settings.
  arXiv  Detail & Related papers  (2026-07-22T18:38:20Z)
• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors [61.34273238077091]
  We present a novel method for generating orbital videos from a single image of an object.<n>Our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-14T05:35:46Z)
• DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional Inpainting [0.8602553195689513]
  We propose DogWeave, a model-based framework for reconstructing high-fidelity 3D canine models from a single RGB image.<n>DogWeave improves geometry by refining a coarsely-initiated parametric mesh into a detailed SDF representation.<n>DogWeave produces complete, realistic 3D models and outperforms state-of-the-art single image to 3d reconstruction methods in both shape accuracy and texture realism for canines.
  arXiv  Detail & Related papers  (2026-03-08T03:35:49Z)
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
  We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
  arXiv  Detail & Related papers  (2025-08-05T04:50:29Z)
• C-DOG: Multi-View Multi-instance Feature Association Using Connected δ-Overlap Graphs [4.576442835703357]
  We introduce C-DOG (Connected delta-Overlap Graph), an algorithm for robust geometrical feature association.<n>In a C-DOG graph, two nodes representing 2D feature points from distinct views are connected by an edge if they correspond to the same 3D point.<n>Experiments on synthetic benchmarks demonstrate that C-DOG not only outperforms geometry-based baseline algorithms but also remains remarkably robust under demanding conditions.
  arXiv  Detail & Related papers  (2025-07-18T17:23:45Z)
• CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis [10.207899254360374]
  3D GANs based on 3D Gaussian splatting have been proposed for high quality synthesis of human heads.<n>Existing methods stabilize training and enhance rendering quality from steep viewpoints by conditioning the random latent vector on the current camera position.<n>We introduce CGS-GAN, a novel 3D Gaussian splatting GAN framework that enables stable training and high-quality 3D-consistent synthesis of human heads without relying on view-conditioning.
  arXiv  Detail & Related papers  (2025-05-23T07:56:25Z)
• GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators [24.67369444661137]
  GCA-3D is a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation.<n>We introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner.<n>Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.
  arXiv  Detail & Related papers  (2024-12-20T02:13:11Z)
• LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors [107.83398512719981]
  Single-image 3D reconstruction remains a fundamental challenge in computer vision.<n>Recent advances in Latent Video Diffusion Models offer promising 3D priors learned from large-scale video data.<n>We propose LiftImage3D, a framework that effectively releases LVDMs' generative priors while ensuring 3D consistency.
  arXiv  Detail & Related papers  (2024-12-12T18:58:42Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• 3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning [19.763523500564542]
  CHASE is a novel framework that achieves dense-input-level performance using only sparse inputs. We introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set. While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets.
  arXiv  Detail & Related papers  (2024-08-19T02:46:23Z)
• GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
  We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view. The model learns to generate 3D objects represented by sets of GS ellipsoids. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
  arXiv  Detail & Related papers  (2024-07-05T03:43:08Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)

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.