Paper deep dive
GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior
Yajiao Xiong, Youyu Luan, Xiaoyu Zhou, Yongtao Wang
Intelligence
Status: succeeded | Model: Gemma-4-26B-A4B | Prompt: intel-v1 | Confidence: 95%
Last extracted: 9/30/2026, 7:12:42 AM
Summary
The paper titled 'GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior' by Yajiao Xiong et al. proposes a framework for single-image novel view synthesis. It utilizes 3D Gaussian Splatting to model foreground and background separately, aligning them via geometric optimization. A video diffusion model is conditioned using a Dual-Stream Masking mechanism that combines rendered validity masks and geometry-aware warping. The method aims to improve geometric accuracy and visual quality while allowing scene editing. Note: The paper was withdrawn by the author shortly after submission.
Entities (6)
Relation Signals (6)
Yajiao Xiong → authored → GenNVS
confidence 99% · Authors:Yajiao Xiong... Title:GenNVS...
GenNVS → solves → Novel View Synthesis
confidence 96% · We present GenNVS, a framework for geometry-enhanced novel view synthesis
GenNVS → uses → 3D Gaussian Splatting
confidence 95% · Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting
GenNVS → conditions → Video Diffusion Model
confidence 92% · This scene conditions a video diffusion model through the proposed Dual-Stream Masking mechanism
Dual-Stream Masking → utilizes → rendered validity masks
confidence 90% · which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping.
Dual-Stream Masking → utilizes → geometry-aware warping
confidence 90% · which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping.
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Abstract:Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent diffusion-based approaches produce plausible results, but they often struggle to preserve the geometric structure and spatial coherence of foreground objects. We present GenNVS, a framework for geometry-enhanced novel view synthesis via a disentangled 3D prior. Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting and aligns them through a coarse-to-fine geometric optimization process to form a unified 3D scene. This scene conditions a video diffusion model through the proposed Dual-Stream Masking mechanism, which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping. Experimental results show that GenNVS performs favorably against recent methods in both visual quality and geometric accuracy, while naturally supporting flexible scene editing.
Tags
Links
- Source: https://arxiv.org/abs/2609.34579v2
- Canonical: https://arxiv.org/abs/2609.34579v2
PDF not stored locally. Use the link above to view on the source site.
Full Text
4,440 characters extracted from source content.
Expand or collapse full text
Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2609.34579v2 (cs) This paper has been withdrawn by Yajiao Xiong [Submitted on 28 Sep 2026 (v1), last revised 29 Sep 2026 (this version, v2)] Title:GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior Authors:Yajiao Xiong, Youyu Luan, Xiaoyu Zhou, Yongtao Wang View a PDF of the paper titled GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior, by Yajiao Xiong and 3 other authors No PDF available, click to view other formats Abstract:Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent diffusion-based approaches produce plausible results, but they often struggle to preserve the geometric structure and spatial coherence of foreground objects. We present GenNVS, a framework for geometry-enhanced novel view synthesis via a disentangled 3D prior. Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting and aligns them through a coarse-to-fine geometric optimization process to form a unified 3D scene. This scene conditions a video diffusion model through the proposed Dual-Stream Masking mechanism, which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping. Experimental results show that GenNVS performs favorably against recent methods in both visual quality and geometric accuracy, while naturally supporting flexible scene editing. Comments: author errors Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.34579 [cs.CV] (or arXiv:2609.34579v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2609.34579 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yajiao Xiong [view email] [v1] Mon, 28 Sep 2026 08:23:48 UTC (6,421 KB) [v2] Tue, 29 Sep 2026 08:47:01 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior, by Yajiao Xiong and 3 other authorsWithdrawn No license for this version due to withdrawn Current browse context: cs.CV < prev | next > new | recent | 2026-09 Change to browse by: cs cs.AI References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?) mathjaxToggle(); We gratefully acknowledge support from our major funders, member institutions, , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from