Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment

• URL: http://arxiv.org/abs/2512.08930v1
• Date: Tue, 09 Dec 2025 18:59:52 GMT
• Title: Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment
• Authors: Youming Deng, Songyou Peng, Junyi Zhang, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, Lucy Chai,
• Abstract summary: We introduce Selfi, a self-improving 3D reconstruction pipeline via feature alignment.<n>We train a lightweight feature adapter using a reprojection-based consistency loss.<n>This enables state-of-the-art performance in both NVS and camera pose estimation.
• Score: 15.822150318879052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. Recent vision foundation models like VGGT take an orthogonal approach -- 3D knowledge is gained implicitly through training data and loss objectives, enabling feed-forward prediction of both camera parameters and 3D representations directly from a set of uncalibrated images. While flexible, VGGT features lack explicit multi-view geometric consistency, and we find that improving such 3D feature consistency benefits both NVS and pose estimation tasks. We introduce Selfi, a self-improving 3D reconstruction pipeline via feature alignment, transforming a VGGT backbone into a high-fidelity 3D reconstruction engine by leveraging its own outputs as pseudo-ground-truth. Specifically, we train a lightweight feature adapter using a reprojection-based consistency loss, which distills VGGT outputs into a new geometrically-aligned feature space that captures spatial proximity in 3D. This enables state-of-the-art performance in both NVS and camera pose estimation, demonstrating that feature alignment is a highly beneficial step for downstream 3D reasoning.

Related papers

• AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models [42.57469056850227]
  Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control.<n>We propose a novel framework that integrates depth estimation into VLA models to enrich 3D feature representations.
  arXiv  Detail & Related papers  (2026-02-11T09:57:32Z)
• Semantic Causality-Aware Vision-Based 3D Occupancy Prediction [63.752869043357585]
  Vision-based 3D semantic occupancy prediction is a critical task in 3D vision.<n>Existing methods, however, often rely on modular pipelines.<n>We propose a novel causal loss that enables holistic, end-to-end supervision of the modular 2D-to-3D transformation pipeline.
  arXiv  Detail & Related papers  (2025-09-10T08:29:22Z)
• 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)
• Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image [10.648593818811976]
  Existing approaches often rely on fine-tuning pretrained 2D diffusion models or directly generating 3D information through fast network inference.<n>We present a novel method that seamlessly integrates geometry and perception information without requiring additional model training.<n> Experimental results show that we outperform existing methods on novel view synthesis and 3D reconstruction, demonstrating robust and consistent 3D object generation.
  arXiv  Detail & Related papers  (2025-06-26T11:22:06Z)
• ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction [16.03389355810877]
  We introduce the simple idea of adaptive view planning to multi-view synthesis.<n>We generate a sequence of views, leveraging temporal consistency to enhance 3D coherence.
  arXiv  Detail & Related papers  (2025-05-13T05:31:59Z)
• VGGT: Visual Geometry Grounded Transformer [61.37669770946458]
  VGGT is a feed-forward neural network that directly infers all key 3D attributes of a scene.<n>Network achieves state-of-the-art results in multiple 3D tasks.
  arXiv  Detail & Related papers  (2025-03-14T17:59:47Z)
• Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis [25.898616784744377]
  Given a sparse set of observed views, the observations may not provide sufficient direct evidence to obtain complete and accurate 3D.<n>We propose SparseAGS, a method that adapts this analysis-by-synthesis approach by: a) including novel-view-synthesis-based generative priors in conjunction with photometric objectives to improve the quality of the inferred 3D, and b) explicitly reasoning about outliers and using a discrete search with a continuous optimization-based strategy to correct them.
  arXiv  Detail & Related papers  (2024-12-04T18:59:24Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• Towards Realistic 3D Embedding via View Alignment [53.89445873577063]
  This paper presents an innovative View Alignment GAN (VA-GAN) that composes new images by embedding 3D models into 2D background images realistically and automatically. VA-GAN consists of a texture generator and a differential discriminator that are inter-connected and end-to-end trainable.
  arXiv  Detail & Related papers  (2020-07-14T14:45:00Z)

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.