Research map / 3D vision / Gaussian splatting
Sharp Monocular View Synthesis in Less Than a Second
Lars Mescheder, Wei Dong, Shiwei Li, Xuyang BAI, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan Richter and 1 more
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 changed | Where | Measured | Effect |
|---|---|---|---|
| train Flash3D on SHARP's in-house synthetic data (ablation) | Flash3D · Middlebury | DISTS: 0.359 -> 0.325 (3%), 0.433 (28%) | No clear effect |
| apply perceptual loss with Gram term tuned to ResNet-50 features (ablation) | SHARP · benchmarks | DISTS: improves DISTS by 62% and 47% | Improved |
| add tuned perceptual loss (ablation) | SHARP · benchmarks | rendering latency: reduces latency by 49% and 36% | Improved |
| apply perceptual loss to the whole rendered image instead of only occluded patches (ablation) | SHARP · qualitative | visual plausibility | Improved |
| add learned depth adjustment module during training (ablation) | SHARP · ablation (supplement) | image sharpness | Improved |
| add self-supervised finetuning on real images (ablation) | SHARP · ablation (supplement) | visual crispness | Improved |
| unfreeze depth decoder and low-res encoder instead of frozen monodepth (ablation) | SHARP · transparent and reflective surfaces | view synthesis fidelity | Improved |
| add regularizers (ablation) | SHARP · ablation (supplement) | artifacts | Improved |
| use SHARP instead of Gen3C | SHARP vs Gen3C · ScanNet++ | synthesis time (s): 836.455 -> 0.911 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Gen3C — GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (CVPR 2025) · better on 12 of 12 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
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.88)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.88)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.88)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.88)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.88)
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.87)
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.
