Lune

CVPR2025Top-tier venue

MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model

Chenjie Cao, Chaohui Yu, Shang Liu, Fan Wang, Xiangyang Xue, Yanwei Fu

Abstract

%& '() +,-./01+/2 3"/4 5/6505(0+7"-/ !3# \%& '() 52(01+/2 +,5/)8(."5+(, !9# %& "9)(** ")3+5)"): 5")-/5 ",4 )/'/)/,9/ 1+/2* !"#%\%&%'()" (&+", !"# & '()" (&+", Figure 1. The proposed MVGenMaster handles various NVS scenarios properly as a master, including (a) NVS based on single-view text-to-image conditions, (b) interpolation between two known views, and (c) flexible NVS with variable reference views and arbitrary target views. MVGenMaster enables all tasks above with a single forward process without sophisticated iterative inference and dataset updating.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

7 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
  • Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
  • Correspondence-Attention Alignment for Multi-View Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Correspondence-Attention Alignment for Multi-View Diffusion Models cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Correspondence-Attention Alignment for Multi-View Diffusion Models cites Denoising Diffusion Probabilistic Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites High-Resolution Image Synthesis with Latent Diffusion Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites Denoising Diffusion Probabilistic Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites Denoising Diffusion Implicit Models
  • Positional Encoding Field cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Positional Encoding Field cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Positional Encoding Field cites SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
  • ORV: 4D Occupancy-centric Robot Video Generation cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
  • SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations cites High-Resolution Image Synthesis with Latent Diffusion Models
  • SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations cites Denoising Diffusion Implicit Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers7

  1. Positional Encoding FieldYunpeng Bai, Haoxiang Li, Qixing HuangICLR 2026 · 22 citations
  2. ORV: 4D Occupancy-centric Robot Video GenerationXiuyu Yang, Bohan Li, Shaocong Xu, Nan Wang et al.CVPR 2026 · 19 citations
  3. SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited ObservationsSongchun Zhang, Huiyao Xu, Sitong Guo, Zhongwei Xie et al.ICCV 2025 · 6 citations
  4. Towards Realistic and Consistent Orbital Video Generation via 3D Foundation PriorsRong Wang, Ruyi Zha, Ziang Cheng, Jiayu Yang et al.CVPR 2026
  5. Correspondence-Attention Alignment for Multi-View Diffusion ModelsMinkyung Kwon, Jinhyeok Choi, Jiho Park, Seonghu Jeon et al.CVPR 2026

Builds on53

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
  4. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  5. SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations

Related papers

  1. MAGREF: Masked Guidance for Any-Reference Video Generation with Subject DisentanglementYufan Deng, Yuanyang Yin, Xun Guo, Yizhi Wang et al.ICLR 2026 · 20 citations
  2. MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free RectificationTianchi Xing, Bonan Li, Congying Han, Xinmin Qiu et al.ICML 2025
  3. MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D EditingChenjie Cao, Chaohui Yu, Fan Wang, Xiangyang Xue et al.NeurIPS 2024 · 36 citations
  4. MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor ScenesRuijie Lu, Yixin Chen, Junfeng Ni, Baoxiong Jia et al.CVPR 2025
  5. Mv-Adapter: Multi-View Consistent Image Generation Made EasyZehuan Huang, Yuan-Chen Guo, Haoran Wang, Ran Yi et al.ICCV 2025 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines