3DSS is the first differentiable surface splatting renderer that recovers shape, spatially-varying BRDF materials, and HDR illumination from multi-view images via a coverage-based compositing model derived from reconstruction kernels.
Advances in neural information processing systems , volume=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
years
2026 9representative citing papers
Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
A Green-integral neural solver enforces wave physics via nonlocal integral constraints and FFT acceleration to solve the Helmholtz equation more efficiently than standard PINNs on heterogeneous seismic benchmarks.
SpUDD defines superpower contours from power diagrams of unsigned distance samples, proves convergence to the true surface, and uses them to generate approximating polygonal meshes that outperform prior strategies.
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
Physics-informed constraints on implicit neural representations yield more accurate and stable predictions of stirred-tank flows than purely data-driven models when training data is scarce, with diminishing returns at larger dataset sizes.
citing papers explorer
-
3DSS: 3D Surface Splatting for Inverse Rendering
3DSS is the first differentiable surface splatting renderer that recovers shape, spatially-varying BRDF materials, and HDR illumination from multi-view images via a coverage-based compositing model derived from reconstruction kernels.
-
Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel
Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.
-
Soft Anisotropic Diagrams for Differentiable Image Representation
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
-
A Green-Integral-Constrained Neural Solver with Stochastic Physics-Informed Regularization
A Green-integral neural solver enforces wave physics via nonlocal integral constraints and FFT acceleration to solve the Helmholtz equation more efficiently than standard PINNs on heterogeneous seismic benchmarks.
-
SpUDD: Superpower Contouring of Unsigned Distance Data
SpUDD defines superpower contours from power diagrams of unsigned distance samples, proves convergence to the true surface, and uses them to generate approximating polygonal meshes that outperform prior strategies.
-
A Few-Step Generative Model on Cumulative Flow Maps
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
-
Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
-
Accelerated and data-efficient flow prediction in stirred tanks via physics-informed learning
Physics-informed constraints on implicit neural representations yield more accurate and stable predictions of stirred-tank flows than purely data-driven models when training data is scarce, with diminishing returns at larger dataset sizes.
- FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives