A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.
ACM SIGGRAPH Computer Graphics21(4), 163–169 (1987)
12 Pith papers cite this work, alongside 10,197 external citations. Polarity classification is still indexing.
12
Pith papers citing it
10.2k
external citations · external index
years
2026 12representative citing papers
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
Ram-pressure suppression of interface folding in fast-cooling TRMLs produces Ė_cool ∝ Da^{1/4} scaling.
The resolution independence of cooling rates in TRML simulations is an artifact of opposing numerical effects with no physical basis, and phase structure converges only when the turbulent Field length (where eddy turnover time equals cooling time) is resolved.
SEM-ROVER generates large multiview-consistent 3D urban driving scenes via semantic-conditioned diffusion on Σ-Voxfield voxel grids with progressive outpainting and deferred rendering.
A neural-field plus differentiable FEM pipeline recovers spatially varying thermal diffusivity on reconstructed 3D objects from synthetic thermal sequences and partially transfers to held-out heating/cooling conditions.
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
A part-based neural deformation model disentangles motion and shape spaces in a diffusion-based 4D generator, outperforming prior work on unconditional and conditional 4D shape tasks.
SAND speeds up neural implicit surface sampling by adaptively terminating MLP evaluations using a learned volumetric depth map and per-layer output tails.
Zivid 2M+ 60 outperformed Intel RealSense D405, PMD Flexx2, and Stereolabs ZED 2i on all tested specimens and metrics; ZED ranked second on real tissue but last on the phantom.
A survey of 3D representation families that highlights the shift from discrete explicit formats to continuous implicit neural and primitive-based ones.
citing papers explorer
-
Diffusion-Based Material Regularization for Physics-Based Inverse Rendering
A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.
-
MeshFlow: Mesh Generation with Equivariant Flow Matching
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
-
The Origin of Da Scaling: Suppressed Cooling in Fast-Cooling Mixing Layers
Ram-pressure suppression of interface folding in fast-cooling TRMLs produces Ė_cool ∝ Da^{1/4} scaling.
-
Ceci n'est pas une Couche de M\'elange: The Meaning of Resolved Turbulent Radiative Mixing
The resolution independence of cooling rates in TRML simulations is an artifact of opposing numerical effects with no physical basis, and phase structure converges only when the turbulent Field length (where eddy turnover time equals cooling time) is resolved.
-
SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
SEM-ROVER generates large multiview-consistent 3D urban driving scenes via semantic-conditioned diffusion on Σ-Voxfield voxel grids with progressive outpainting and deferred rendering.
-
Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations
A neural-field plus differentiable FEM pipeline recovers spatially varying thermal diffusivity on reconstructed 3D objects from synthetic thermal sequences and partially transfers to held-out heating/cooling conditions.
-
Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
-
Learning Neural Deformation Representation for 4D Dynamic Shape Generation
A part-based neural deformation model disentangles motion and shape spaces in a diffusion-based 4D generator, outperforming prior work on unconditional and conditional 4D shape tasks.
-
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
SAND speeds up neural implicit surface sampling by adaptively terminating MLP evaluations using a learned volumetric depth map and per-layer output tails.
-
Comparing Commercial Depth Sensor Accuracy for Medical Applications
Zivid 2M+ 60 outperformed Intel RealSense D405, PMD Flexx2, and Stereolabs ZED 2i on all tested specimens and metrics; ZED ranked second on real tissue but last on the phantom.
-
Recent Advances and Trends in Learning-based 3D Representations
A survey of 3D representation families that highlights the shift from discrete explicit formats to continuous implicit neural and primitive-based ones.
- VisDom: Sparse Novel View Synthesis with Visible Domain Constraint