paper-with-me

홈 › Papers

Sharp Monocular View Synthesis in Less Than a Second

2025-12-11 · Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan R. Richter, Vladlen Koltun arxiv

We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Experimental results demonstrate that SHARP delivers robust zero-shot generalization across datasets. It sets a new state of the art on multiple datasets, reducing LPIPS by 25-34% and DISTS by 21-43% versus the best prior model, while lowering the synthesis time by three orders of magnitude. Code and weights are provided at https://github.com/apple/ml-sharp

📄 PDF Abstract BibTeX arXiv:2512.10685

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot Generalization

Similar Papers 제목 키워드 기반

DyBluRF: Dynamic Deblurring Neural Radiance Fields for Blurry Monocular Video

2023-12-21 · Minh-Quan Viet Bui, Jongmin Park, Jihyong Oh, Munchurl Kim

Neural Radiance Fields (NeRF), initially developed for static scenes, have inspired many video novel view synthesis techniques. However, the challenge for video view synthesis arises from motion blur, a consequence of ob…

DeblurringNeRFNovel View Synthesis

UniSHARP: Universal Sharp Monocular View Synthesis

2026-06-05 · Meixi Song, Dizhe Zhang, Hao Ren, Ruiyang Zhang 외 arxiv

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-…

DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting

2025-06-26 · Yeon-Ji Song, Jaein Kim, Byung-Ju Kim, Byoung-Tak Zhang

Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Ex…

3D geometryNovel View Synthesis

Dynamic Neural Radiance Field From Defocused Monocular Video

2024-07-08 · Xianrui Luo, Huiqiang Sun, Juewen Peng, Zhiguo Cao

Dynamic Neural Radiance Field (NeRF) from monocular videos has recently been explored for space-time novel view synthesis and achieved excellent results. However, defocus blur caused by depth variation often occurs in vi…

Dynamic ReconstructionNeRFNovel View Synthesis

Fast Non-Rigid Radiance Fields from Monocularized Data

2022-12-02 · Moritz Kappel, Vladislav Golyanik, Susana Castillo, Christian Theobalt 외

The reconstruction and novel view synthesis of dynamic scenes recently gained increased attention. As reconstruction from large-scale multi-view data involves immense memory and computational requirements, recent benchma…

3D ReconstructionNovel View Synthesis