Search Results for author:
Found 29 papers, 14 papers with code
UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark
To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment.
Motion Inversion for Video Customization
In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models.
VRMM: A Volumetric Relightable Morphable Head Model
In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling.
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
In practice, users often desire the ability to control object motion and camera movement independently for customized video creation.
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model.
A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization
The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model.
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS).
Ranked #1 on
Video Semantic Segmentation
on VSPW
Stable Segment Anything Model
Thus, our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality, with 3) minimal learnable parameters (0. 08 M) and fast adaptation (by 1 training epoch).
Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery
Though significant progress in human pose and shape recovery from monocular RGB images has been made in recent years, obtaining 3D human motion with high accuracy and temporal consistency from videos remains challenging.
Towards Practical Capture of High-Fidelity Relightable Avatars
Specifically, TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions, enabling realistic relighting and real-time animation for avatars in diverse scenes.
1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving.
1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.
DVIS: Decoupled Video Instance Segmentation Framework
The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement.
Ranked #3 on
Video Panoptic Segmentation
on VIPSeg
Multi-Modal Face Stylization with a Generative Prior
We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces.
Bridging CLIP and StyleGAN through Latent Alignment for Image Editing
More specifically, our efforts consist of three parts: 1) a data-free training strategy to train latent mappers to bridge the latent space of CLIP and StyleGAN; 2) for more precise mapping, temporal relative consistency is proposed to address the knowledge distribution bias problem among different latent spaces; 3) to refine the mapped latent in s space, adaptive style mixing is also proposed.
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
ITTR: Unpaired Image-to-Image Translation with Transformers
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data.
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands.
PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths
It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest.
Ranked #1 on
Point Cloud Completion
on Completion3D
Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
Our insight into the detailed geometry is to introduce a skip-transformer in the SPD to learn the point splitting patterns that can best fit the local regions.
Ranked #5 on
Point Cloud Completion
on ShapeNet
Debiased Self-Training for Semi-Supervised Learning
Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks.
Assessing a Single Image in Reference-Guided Image Synthesis
For Reference-guided Image Synthesis (RIS) tasks, i. e., rendering a source image in the style of another reference image, where assessing the quality of a single generated image is crucial, these metrics are not applicable.
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
Specifically, we first train a self-supervised style encoder on the generic artistic dataset to extract the representations of arbitrary styles.
SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer
However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape.
Exploring Set Similarity for Dense Self-supervised Representation Learning
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
We provide a comprehensive evaluation in experiments, which shows that our model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.
Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration
In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues.
PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
As a result, the network learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target, and thus improves the quality of the predicted complete shape.
Precision Enhancement of 3D Surfaces from Multiple Compressed Depth Maps
In texture-plus-depth representation of a 3D scene, depth maps from different camera viewpoints are typically lossily compressed via the classical transform coding / coefficient quantization paradigm.
