unPIC: A Geometric Multiview Prior for Image to 3D Synthesis
We introduce a hierarchical probabilistic approach to go from a 2D image to multiview 3D: a diffusion "prior" predicts the unseen 3D geometry, which then conditions a diffusion "decoder" to generate novel views of the subject. We use a pointmap-based geometric representation to coordinate the generation of multiple target views simultaneously. We construct a predictable distribution of geometric features per target view to enable learnability across examples, and generalization to arbitrary inputs images. Our modular, geometry-driven approach to novel-view synthesis (called "unPIC") beats competing baselines such as CAT3D, EscherNet, Free3D, and One-2-3-45 on held-out objects from ObjaverseXL, as well as unseen real-world objects from Google Scanned Objects, Amazon Berkeley Objects, and the Digital Twin Catalog.
Code (0)
등록된 구현이 없습니다.
Tasks
3D geometryDecoderImage to 3DNovel View SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction solutions have shown promising results, …
3D Human Reconstruction3D ReconstructionNovel View SynthesisMammoFlow: Multiview Mammogram Synthesis with Anatomically Consistent Flow Matching
Multiview mammography relies on paired craniocaudal (CC) and mediolateral oblique (MLO) views to provide complementary projections of a 3D breast volume, enabling precise anomaly localization. However, acquiring high-qua…
Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
Generating realistic 3D objects from single-view images requires natural appearance, 3D consistency, and the ability to capture multiple plausible interpretations of unseen regions. Existing approaches often rely on fine…
3D Generation3D ReconstructionNovel View SynthesisNeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view …
3D Generation3D geometry3D ReconstructionNeRFOmni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images
This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of …
Novel View SynthesisScene UnderstandingScene Generation