Search Results for author:
Found 22 papers, 11 papers with code
Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
In this work, we introduce Lux Post Facto, a novel portrait video relighting method that produces both photorealistic and temporally consistent lighting effects.
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer.
Fitting Spherical Gaussians to Dynamic HDRI Sequences
We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps.
DifFRelight: Diffusion-Based Facial Performance Relighting
We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation.
Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM
We introduce Chat2Layout, a novel interactive furniture layout generation system that extends the functionality of MLLMs into the realm of interactive layout design.
Mesh-Guided Neural Implicit Field Editing
We first introduce a differentiable method using marching tetrahedra for polygonal mesh extraction from the neural implicit field and then design a differentiable color extractor to assign colors obtained from the volume renderings to this extracted mesh.
AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control
Neural implicit fields are powerful for representing 3D scenes and generating high-quality novel views, but it remains challenging to use such implicit representations for creating a 3D human avatar with a specific identity and artistic style that can be easily animated.
NeRF-Art: Text-Driven Neural Radiance Fields Stylization
As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-quality novel view synthesis from multi-view images.
Water Simulation and Rendering from a Still Photograph
We propose an approach to simulate and render realistic water animation from a single still input photograph.
DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points
To make the local features aware of the global context and improve their matching accuracy, we introduce DenseGAP, a new solution for efficient Dense correspondence learning with a Graph-structured neural network conditioned on Anchor Points.
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images.
DisUnknown: Distilling Unknown Factors for Disentanglement Learning
In this paper, we adopt a general setting where all factors that are hard to label or identify are encapsulated as a single unknown factor.
Exemplar-Based 3D Portrait Stylization
In the second texture style transfer stage, we focus on performing style transfer on the canonical texture by adopting a differentiable renderer to optimize the texture in a multi-view framework.
Cross-Domain and Disentangled Face Manipulation with 3D Guidance
Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability.
Efficient Semantic Image Synthesis via Class-Adaptive Normalization
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away.
Dynamic Facial Asset and Rig Generation from a Single Scan
We also model the joint distribution between identities and expressions, enabling the inference of the full set of personalized blendshapes with dynamic appearances from a single neutral input scan.
One-Shot Identity-Preserving Portrait Reenactment
This is achieved by a novel landmark disentanglement network (LD-Net), which predicts personalized facial landmarks that combine the identity of the target with expressions and poses from a different subject.
Rethinking Spatially-Adaptive Normalization
Despite its impressive performance, a more thorough understanding of the true advantages inside the box is still highly demanded, to help reduce the significant computation and parameter overheads introduced by these new structures.
Deep Exemplar-based Video Colorization
This paper presents the first end-to-end network for exemplar-based video colorization.
Gated Context Aggregation Network for Image Dehazing and Deraining
Image dehazing aims to recover the uncorrupted content from a hazy image.
Ranked #2 on
Rain Removal
on DID-MDN
Deep Exemplar-based Colorization
More importantly, as opposed to other learning-based colorization methods, our network allows the user to achieve customizable results by simply feeding different references.
Progressive Color Transfer with Dense Semantic Correspondences
The proposed method can be successfully extended from one-to-one to one-to-many color transfer.
