BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
DySurface combines deformed Gaussians with implicit SDFs via a VoxGS-DSDF voxel-grid branch to produce watertight, temporally consistent 4D surfaces while preserving rendering quality.
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
A delighting network trained via Dataset Latent Modulation on heterogeneous OLAT and Light Stage data enables high-quality in-the-wild facial reflectance capture from video and produces the NeRSemble-Scan dataset.
2D-SuGaR improves 2D Gaussian Splatting with monocular priors and targeted initialization/pruning to achieve state-of-the-art mesh reconstruction on the DTU dataset while retaining high-quality novel view synthesis.
FieryGS couples MLLM-based material reasoning with simplified combustion simulation and unified fire/smoke/3DGS rendering to synthesize controllable, scene-consistent fire in reconstructed real-world scenes.
Comparative study of DS-NeRF, TensoRF, and HashNeRF with depth-supervision and architectural variants finds no conclusive outperformance under equal training time but identifies which design choices transfer to low-data, low-compute regimes.
citing papers explorer
-
BodyReLux: Temporally Consistent Full-Body Video Relighting
BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
DySurface combines deformed Gaussians with implicit SDFs via a VoxGS-DSDF voxel-grid branch to produce watertight, temporally consistent 4D surfaces while preserving rendering quality.
-
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
-
Learning a Delighting Prior for Facial Appearance Capture in the Wild
A delighting network trained via Dataset Latent Modulation on heterogeneous OLAT and Light Stage data enables high-quality in-the-wild facial reflectance capture from video and produces the NeRSemble-Scan dataset.
-
2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction
2D-SuGaR improves 2D Gaussian Splatting with monocular priors and targeted initialization/pruning to achieve state-of-the-art mesh reconstruction on the DTU dataset while retaining high-quality novel view synthesis.
-
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
FieryGS couples MLLM-based material reasoning with simplified combustion simulation and unified fire/smoke/3DGS rendering to synthesize controllable, scene-consistent fire in reconstructed real-world scenes.
-
Low-Cost Neural Radiance Fields
Comparative study of DS-NeRF, TensoRF, and HashNeRF with depth-supervision and architectural variants finds no conclusive outperformance under equal training time but identifies which design choices transfer to low-data, low-compute regimes.
- Functionalization via Structure Completion and Motion Rectification