Research map / 3D vision / NeRF and radiance fields
Real-Time Neural Rasterization for Large Scenes
Jeffrey Yunfan Liu, Yun Chen, Ze Yang, Jingkang Wang, Sivabalan Manivasagam, Raquel Urtasun
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 |
|---|---|---|---|
| add MLP fragment shader on neural textures (ablation) | NeuRas · PandaSet log-53 | PSNR: 24.48 -> 25.34 | Improved |
| add view direction input to MLP shader (ablation) | NeuRas · PandaSet log-53 | PSNR: 25.01 -> 25.34 | Improved |
| add vector quantization of texture features (ablation) | NeuRas · PandaSet log-53 | Storage (MB): 4644 -> 394 | Improved |
| add vector quantization of texture features (ablation) | NeuRas · PandaSet log-53 lane shift | FID@2m: 81.5 -> 78.2 | Improved |
| add vector quantization of texture features (ablation) | NeuRas · PandaSet log-53 interpolation | PSNR: 25.46 -> 25.34 | No clear effect |
| decimate scaffold mesh to fewer vertices (50K vs 500K) | NeuRas · PandaSet | visual quality | No clear effect |
| use NeuRas rasterization instead of volumetric rendering of UniSim | UniSim · PandaSet | FPS: 1.4 -> 120 | Improved |
| render NeRF-extracted meshes with NeuRas (poor geometry) | Instant-NGP · BlendedMVS Church | PSNR: 23.55 -> 20.26 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- UniSim — UniSim: A Neural Closed-Loop Sensor Simulator (CVPR 2023) · better on 3 of 6 shared results
- MobileNeRF — MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures (CVPR 2023) · better on 0 of 1 shared result
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
- NPBG++: Accelerating Neural Point-Based Graphics (CVPR 2022 · similarity 0.90)
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ECCV 2020 · similarity 0.89)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.87)
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.87)
- HashPoint: Accelerated Point Searching and Sampling for Neural Rendering (CVPR 2024 · similarity 0.87)
- Real3D: The Curious Case of Neural Scene Degeneration (AAAI 2024 · 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.
