Search Results for author:
Found 29 papers, 13 papers with code
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects.
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field.
DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing
Our key idea is to capture the semantics of the two images by fitting two LoRAs to them respectively, and interpolate between both the LoRA parameters and the latent noises to ensure a smooth semantic transition, where correspondence automatically emerges without the need for annotation.
MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
In this work, we propose Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR (\textbf{MATLABER}) that leverages a novel latent BRDF auto-encoder for material generation.
AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars
Our method edits the full head in a canonical space, and then propagates these edits to remaining time steps via a pretrained deformation network.
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects.
GVP: Generative Volumetric Primitives
Advances in 3D-aware generative models have pushed the boundary of image synthesis with explicit camera control.
HQ3DAvatar: High Quality Controllable 3D Head Avatar
This paper presents a novel approach to building highly photorealistic digital head avatars.
AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
Traditional modeling pipelines keep an asset library storing unique object templates, which is both versatile and memory efficient in practice.
Grid-guided Neural Radiance Fields for Large Urban Scenes
An alternative solution is to use a feature grid representation, which is computationally efficient and can naturally scale to a large scene with increased grid resolutions.
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Most in-the-wild images are stored in Low Dynamic Range (LDR) form, serving as a partial observation of the High Dynamic Range (HDR) visual world.
gCoRF: Generative Compositional Radiance Fields
We start with a global generative model (GAN) and learn to decompose it into different semantic parts using supervision from 2D segmentation masks.
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene.
GAN2X: Non-Lambertian Inverse Rendering of Image GANs
2D images are observations of the 3D physical world depicted with the geometry, material, and illumination components.
Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Our model can disentangle the geometry and appearance variations in the scene, i. e., we can independently sample from the geometry and appearance spaces of the generative model.
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
The wide span of viewing positions within these scenes yields multi-scale renderings with very different levels of detail, which poses great challenges to neural radiance field and biases it towards compromised results.
Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
In this paper, we propose Generative Occupancy Fields (GOF), a novel model based on generative radiance fields that can learn compact object surfaces without impeding its training convergence.
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint as regularization to learn valid 3D radiance fields from 2D images.
Talk-to-Edit: Fine-Grained Facial Editing via Dialog
In this work, we propose Talk-to-Edit, an interactive facial editing framework that performs fine-grained attribute manipulation through dialog between the user and the system.
Ranked #1 on
Fine-Grained Facial Editing
on CelebA-Dialog
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner.
Self-Supervised Scene De-occlusion
This is achieved via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner.
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Learning a good image prior is a long-term goal for image restoration and manipulation.
Channel Equilibrium Networks for Learning Deep Representation
Unlike prior arts that simply removed the inhibited channels, we propose to "wake them up" during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation.
Channel Equilibrium Networks
However, over-sparse CNNs have many collapsed channels (i. e. many channels with undesired zero values), impeding their learning ability.
Open Compound Domain Adaptation
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e. g., sunny weather) for achieving high performance on the test data in a target domain (e. g., rainy weather).
Switchable Whitening for Deep Representation Learning
Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods.
Ranked #6 on
Robust Object Detection
on DWD
Self-Supervised Learning via Conditional Motion Propagation
Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem.
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances.
Ranked #3 on
All-day Semantic Segmentation
on All-day CityScapes
Spatial As Deep: Spatial CNN for Traffic Scene Understanding
Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored.
Ranked #50 on
Lane Detection
on CULane
