DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

• URL: http://arxiv.org/abs/2505.05473v1
• Date: Thu, 08 May 2025 17:59:47 GMT
• Title: DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
• Authors: Qitao Zhao, Amy Lin, Jeff Tan, Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani,
• Abstract summary: We propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images.<n>Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame.<n>We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches.
• Score: 53.70278210626701
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Current Structure-from-Motion (SfM) methods typically follow a two-stage pipeline, combining learned or geometric pairwise reasoning with a subsequent global optimization step. In contrast, we propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images. Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame and employs a transformer-based denoising diffusion model to predict them from multi-view inputs. To address practical challenges in training diffusion models with missing data and unbounded scene coordinates, we introduce specialized mechanisms that ensure robust learning. We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches while naturally modeling uncertainty.

Related papers

• Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT [10.984522161856955]
  3D reconstruction is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics.<n>Deep learning has catalyzed a paradigm shift in 3D reconstruction.<n>New models employ a unified deep network to jointly infer camera poses and dense geometry directly from an Unconstrained set of images in a single forward pass.
  arXiv  Detail & Related papers  (2025-07-11T09:41:54Z)
• MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation [19.46962637673285]
  MV-CoLight is a framework for illumination-consistent object compositing in 2D and 3D scenes.<n>We employ a Hilbert curve-based mapping to align 2D image inputs with 3D Gaussian scene representations seamlessly.<n> Experiments demonstrate state-of-the-art harmonized results across standard benchmarks and our dataset.
  arXiv  Detail & Related papers  (2025-05-27T17:53:02Z)
• Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models [96.97910688908956]
  We introduce the first zero-shot approach for Video Semantic (VSS) based on pre-trained diffusion models. We propose a framework tailored for VSS based on pre-trained image and video diffusion models. Experiments show that our proposed approach outperforms existing zero-shot image semantic segmentation approaches.
  arXiv  Detail & Related papers  (2024-05-27T08:39:38Z)
• Curved Diffusion: A Generative Model With Optical Geometry Control [56.24220665691974]
  The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a textto-image diffusion model with the particular lens used in image rendering.
  arXiv  Detail & Related papers  (2023-11-29T13:06:48Z)
• Light Field Diffusion for Single-View Novel View Synthesis [32.59286750410843]
  Single-view novel view synthesis (NVS) is important but challenging in computer vision. Recent advancements in NVS have leveraged Denoising Diffusion Probabilistic Models (DDPMs) for their exceptional ability to produce high-fidelity images. We present Light Field Diffusion (LFD), a novel conditional diffusion-based approach that transcends the conventional reliance on camera pose matrices.
  arXiv  Detail & Related papers  (2023-09-20T03:27:06Z)
• Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction [77.69363640021503]
  3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. We present SSDNeRF, a unified approach that employs an expressive diffusion model to learn a generalizable prior of neural radiance fields (NeRF) from multi-view images of diverse objects.
  arXiv  Detail & Related papers  (2023-04-13T17:59:01Z)
• DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion [9.294501649791016]
  Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM) We formulate the two-view SfM problem as a maximum likelihood estimation (MLE) and solve it with the proposed framework, denoted as DeepMLE. Our method significantly outperforms the state-of-the-art end-to-end two-view SfM approaches in accuracy and generalization capability.
  arXiv  Detail & Related papers  (2022-10-11T15:07:25Z)
• RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild [73.1276968007689]
  We describe a data-driven method for inferring the camera viewpoints given multiple images of an arbitrary object. We show that our approach outperforms state-of-the-art SfM and SLAM methods given sparse images on both seen and unseen categories.
  arXiv  Detail & Related papers  (2022-08-11T17:59:59Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)

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.