novel view synthesis
The task of generating new views of a scene or object from a limited set of input images, often utilizing 3D scene representations or neural rendering techniques to create realistic visualizations.
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
- Anti-Aliased 2D Gaussian Splatting
- Cameras as Relative Positional Encoding
- Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
- EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
- Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
- Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
- FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
- Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
- IBGS: Image-Based Gaussian Splatting
- LinPrim: Linear Primitives for Differentiable Volumetric Rendering
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
- Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
- NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
- Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
- X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
- ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS