AI Paper Atlas

Research map / 3D vision / 3D generation

DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation

Yunhan Yang, Shuo Chen, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Edmund Y. M. Lam, Hengshuang Zhao, Tong He, Xihui Liu

TPAMI 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DreamComposer++ multi-view conditioningZero-1-to-3 · GSO NVS, 4 views, elevation 0PSNR: 20.82 -> 25.25Improved
add DreamComposer++ multi-view conditioningZero-1-to-3 · GSO NVS, 4 views, elevation 30LPIPS: 0.128 -> 0.086Improved
add DreamComposer++ with generated extra viewSyncDreamer · GSO NVSPSNR: 20.05 -> 20.52Improved
add DreamComposer++ with 2 viewsSV3D · GSO NVS, elevation 0LPIPS: 0.3156 -> 0.1441Improved
increase input views from 2 to 6DC-SV3D · GSO NVS, elevation 0PSNR: 19.83 -> 22.21Improved
increase input views from 2 to 6DC-Zero-1-to-3 · GSO NVS, elevation 0PSNR: 20.38 -> 26.99Improved
freeze the pretrained diffusion UNet (ablation)DC-SyncDreamer · GSO NVSPSNR: 15.96 -> 20.52Improved
add reconstruction MSE loss in stage two (ablation)DC-SyncDreamer · GSO NVSPSNR: 16.18 -> 20.52Improved
add view-conditioning cross-attention in 3D lifting (ablation)DC-SyncDreamer · GSO NVSPSNR: 19.04 -> 20.52Improved
add view-aware attention (ablation)DC-SV3D (2 views) · GSO NVS, elevation 0LPIPS: 0.2968 -> 0.1441Improved
use attention-based fusion instead of convolution (ablation)DC-SV3D (2 views) · GSO NVS, elevation 0PSNR: 17.98 -> 19.83Improved
use ground-truth latents instead of Lift3D rendered features (ablation)DC-SV3D · video generationvisual qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy