Problem
Research questions and friction points this paper is trying to address.
Image-to-3D
geometric fidelity
partial observations
Guiding Image-to-3D Generation with Test-Time Partial Observations
๐ค AI Summary
่ฏฅ็ ็ฉถ้่ฟๅจๆต่ฏๆถๅผๅ
ฅ้จๅๅ ไฝ่งๅฏๆๅฏผ้ข่ฎญ็ป็ๅพๅๅฐ3Dๆจกๅ๏ผๆ้ซ็ๆ3D่ตไบง็ๅ ไฝไฟ็ๅบฆๅ่ง่ง่ดจ้ใ
๐ Abstract
Image-to-3D models can generate visually compelling 3D assets from a single RGB image, but their geometry is often only loosely constrained by the available observations, limiting their use in applications that require geometric fidelity. In many real-world settings, however, partial geometric observations of the object may be available at test time. We introduce a training-free framework for incorporating such evidence into pretrained image-to-3D generative models without retraining or finetuning. To do this, we guide generation using a ray-consistent observation likelihood defined over the model's occupancy representation, combining surface occupancy and free-space evidence. Applied to SAM 3D and its multi-view extension, our approach substantially improves geometric fidelity across different levels of observability, as well as visual quality. Our results demonstrate that pretrained image-to-3D models can effectively integrate partial geometric observations through explicit test-time guidance, complementing their learned generative priors without modifying the underlying model.
Innovation
Methods, ideas, or system contributions that make the work stand out.
test-time partial observations
ray-consistent observation likelihood
occupancy representation
๐ Similar Papers
No similar papers found.
