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.
hub
CVPR , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
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 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.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generalization in AI-generated image detection.
Two-view accumulation per optimizer step is the dominant training lever for hybrid-capture 3DGS, explained by a variance-decomposition framework showing within-regime gradient variance dominates over between-regime variance.
AnimeAdapter is a pretrained lightweight adapter for Stable Diffusion that uses semantic-selective local attention from CLIP and pose-aware conditioning to enable zero-shot fine-grained consistent anime character generation from a single reference image.
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.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired 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.
-
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.
-
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.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generalization in AI-generated image detection.
-
Two-View Accumulation as the Primary Training Lever for Hybrid-Capture Gaussian Splatting: A Variance-Decomposition View of When Gradient Surgery Helps
Two-view accumulation per optimizer step is the dominant training lever for hybrid-capture 3DGS, explained by a variance-decomposition framework showing within-regime gradient variance dominates over between-regime variance.
-
AnimeAdapter: Fine-grained and Consistent Zero-shot Anime Character Generation
AnimeAdapter is a pretrained lightweight adapter for Stable Diffusion that uses semantic-selective local attention from CLIP and pose-aware conditioning to enable zero-shot fine-grained consistent anime character generation from a single reference image.
- HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos